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

    Neuronpedia

    INDEX
    Explanations

    instances of whitespace or empty tokens in the document

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

    foreign words and names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    StoryboardSegue
    -0.69
     autorytatywna
    -0.64
     Wikimedijinoj
    -0.63
    colhead
    -0.63
     defaultstate
    -0.61
    JspWriter
    -0.58
    OGND
    -0.57
    execSQL
    -0.56
    setVerticalGroup
    -0.55
    LEncoder
    -0.55
    POSITIVE LOGITS
    BagConstraints
    0.38
     gwaran
    0.37
     opty
    0.33
     Nosotros
    0.32
     przód
    0.31
     rękaw
    0.30
    ău
    0.29
     drauf
    0.29
    according
    0.29
     depends
    0.29
    Act Density 0.029%

    No Known Activations