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

    Neuronpedia

    INDEX
    Explanations

    mathematical symbols and expressions related to variables and indices

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

    mathematical formulas with indices

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     <<<<<<<<<<<<<<
    -0.68
    findpost
    -0.65
    reportWebVitals
    -0.60
     Signalez
    -0.59
    FormTagHelper
    -0.59
    SharedDtor
    -0.56
    endregion
    -0.55
    saraba
    -0.55
    TagMode
    -0.55
    \{\\
    -0.54
    POSITIVE LOGITS
    xla
    0.31
     surface
    0.29
     J
    0.26
    setattr
    0.26
    xions
    0.25
     Ja
    0.25
    زای
    0.24
     conf
    0.24
     пак
    0.24
    経験
    0.24
    Act Density 0.138%

    No Known Activations