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

    Neuronpedia

    INDEX
    Explanations

    words that describe groupings, categories, or varying degrees of something

    oai_token-act-pair · gemini-2.0-flash

    variety/range

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    gameserver
    -0.88
    دانشنامهٔ
    -0.84
    clearInterval
    -0.82
    LookAnd
    -0.79
    下载附件
    -0.79
     مرئيه
    -0.78
     Мексичка
    -0.76
     joaat
    -0.75
    Portály
    -0.73
    esModule
    -0.72
    POSITIVE LOGITS
     Some
    0.53
     some
    0.50
     partid
    0.50
     several
    0.50
     I
    0.49
     erity
    0.49
     Several
    0.48
     lotes
    0.48
     arbejde
    0.48
    some
    0.47
    Act Density 1.189%

    No Known Activations