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

    Neuronpedia

    INDEX
    Explanations

    Dates

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    εις
    -0.07
    [key
    -0.07
    (cd
    -0.07
    Matches
    -0.07
    자인
    -0.06
    itionally
    -0.06
     Revel
    -0.06
     cloudy
    -0.06
     String
    -0.06
     берег
    -0.06
    POSITIVE LOGITS
     lanç
    0.08
    jj
    0.07
     піс
    0.07
    'article
    0.07
     ชนะ
    0.06
     jumlah
    0.06
    _'
    0.06
     Population
    0.06
    }):
    0.06
     GitHub
    0.06
    Act Density 0.038%

    No Known Activations