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

    Neuronpedia

    INDEX
    Explanations

    numbers and numerical values within the text

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

    code delimiters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     defe
    -0.34
    󠁢
    -0.34
     waw
    -0.32
     poffe
    -0.31
     vios
    -0.31
    Perry
    -0.31
     bel
    -0.31
    minecraft
    -0.31
     Bel
    -0.30
     clin
    -0.29
    POSITIVE LOGITS
    ValueStyle
    0.87
    elemField
    0.59
    endphp
    0.57
    tagext
    0.54
    FieldDescriptor
    0.54
    0.53
    ArrowToggle
    0.53
    adaptiveStyles
    0.53
    FunctionFlags
    0.52
    MigrationBuilder
    0.51
    Act Density 0.183%

    No Known Activations