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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks, specifically periods

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

    code snippets and functions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ujednoznacz
    -0.92
    NameInMap
    -0.75
    InitVars
    -0.73
    RTEX
    -0.71
    endpush
    -0.70
    EndContext
    -0.69
     <=",
    -0.68
    ThroughAttribute
    -0.68
     ſeines
    -0.67
     OMITBAD
    -0.67
    POSITIVE LOGITS
    AlterField
    0.37
     very
    0.28
    ies
    0.28
    1
    0.28
     See
    0.27
     Very
    0.27
     
    0.27
     see
    0.26
     un
    0.26
     c
    0.26
    Act Density 0.026%

    No Known Activations