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

    Neuronpedia

    INDEX
    Explanations

    LaTeX formatting related to mathematical expressions or figures

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

    references like fig, theorem, lemma

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ↵
    -0.48
     
    -0.44
    -
    -0.43
    _
    -0.41
     or
    -0.41
    .
    -0.40
    2
    -0.40
     sp
    -0.39
    *
    -0.39
    '
    -0.37
    POSITIVE LOGITS
    脚注の使い方
    0.85
     surla
    0.82
     Normdatei
    0.76
    нгред
    0.72
    adaptiveStyles
    0.71
     Chwiliwch
    0.71
     CURIAM
    0.70
     resourceCulture
    0.68
    الدراسه
    0.68
    ViewInit
    0.67
    Act Density 0.073%

    No Known Activations