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

    Neuronpedia

    INDEX
    Explanations

    comparative phrases that indicate variability or diversity

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

    Prepositions like "As" and words after them

    np_acts-logits-general · gemini-2.0-flash

    such as

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     edición
    -0.48
     vraie
    -0.48
     edizione
    -0.47
    <>
    -0.47
     verdaderos
    -0.46
     vrai
    -0.46
     verdadeira
    -0.46
     edição
    -0.46
    Banyak
    -0.46
     ')'
    -0.45
    POSITIVE LOGITS
    DockStyle
    0.72
    setVerticalGroup
    0.71
    下载附件
    0.70
     NSCoder
    0.67
    CompleteListener
    0.65
    帖最后由
    0.64
     such
    0.63
     IndexPath
    0.63
    DllImport
    0.62
    moveToFirst
    0.62
    Act Density 0.132%

    No Known Activations