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

    Neuronpedia

    INDEX
    Explanations

    elements related to programming constructs and error handling

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

    Code snippets or mathematical expressions

    np_acts-logits-general · gemini-2.0-flash

    code snippets and mathematical notation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ########.
    -0.81
     intptr
    -0.76
    sizeCache
    -0.73
     мәкал
    -0.71
     فريبيس
    -0.71
    ArrowToggle
    -0.70
    ViewFeatures
    -0.70
    featureID
    -0.69
    TypedDataSet
    -0.68
    elemField
    -0.68
    POSITIVE LOGITS
     None
    0.78
    None
    0.76
     u
    0.51
    ur
    0.46
     openings
    0.45
     đào
    0.45
    partial
    0.44
     espoir
    0.44
    u
    0.43
    liv
    0.43
    Act Density 0.148%

    No Known Activations