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

    Neuronpedia

    INDEX
    Explanations

    words and phrases that are common in tabloid articles about celebrities

    oai_token-act-pair · gemini-2.0-flash

    Punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    روابط
    -0.65
    ǔ
    -0.63
    +#+
    -0.60
    الدراسه
    -0.59
    bootstrapcdn
    -0.57
    balleur
    -0.55
    lielmo
    -0.55
     transférez
    -0.54
    ibia
    -0.54
    eterminate
    -0.54
    POSITIVE LOGITS
    PYX
    0.62
     consultato
    0.61
     ویکی‌پدیا
    0.53
    tagext
    0.49
     snippetHide
    0.48
     rodillas
    0.47
    InjectAttribute
    0.47
    writeFieldEnd
    0.47
    setVerticalGroup
    0.47
    InstanceState
    0.46
    Act Density 0.213%

    No Known Activations