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

    Neuronpedia

    INDEX
    Explanations

    references to moral or altruistic concepts and entities

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

    Samaritan and bacteria names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    TRUNC
    -0.37
    ichord
    -0.36
    cshtml
    -0.35
    Schicken
    -0.35
     piled
    -0.34
     occasioned
    -0.34
     fordern
    -0.34
    MigrationBuilder
    -0.34
    ⠀⠀⠀⠀
    -0.34
     nosi
    -0.33
    POSITIVE LOGITS
     Samaritan
    2.20
     Samar
    2.00
     samar
    1.51
     Samaria
    1.42
    itans
    0.96
     Samara
    0.80
    Personendaten
    0.80
    ScopeManager
    0.77
     autorytatywna
    0.69
    Saman
    0.69
    Act Density 0.004%

    No Known Activations