Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    concepts related to secrecy and the implications of keeping information hidden

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    secrets or concealment

    np_acts-logits-general · gemini-2.0-flash

    secretive or hidden states

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    principalTable
    -0.61
     initComponents
    -0.59
     gynhyrchwyd
    -0.57
    MigrationBuilder
    -0.55
    antMatchers
    -0.55
    ValueStyle
    -0.54
     AssemblyCulture
    -0.53
    ArgsConstructor
    -0.53
    addComponent
    -0.52
    AnchorTagHelper
    -0.51
    POSITIVE LOGITS
     secret
    2.36
     hidden
    2.18
     secrecy
    2.18
     secretive
    2.02
    secret
    2.01
     concealed
    1.94
     secretly
    1.91
     Secret
    1.88
    hidden
    1.87
     hiding
    1.86
    Act Density 0.685%

    No Known Activations