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

    Neuronpedia

    INDEX
    Explanations

    NONINFINGEMENT

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ick
    -0.07
     άλλ
    -0.07
    bitset
    -0.07
    iga
    -0.06
    英语
    -0.06
     Kelly
    -0.06
    ICK
    -0.06
     ebony
    -0.06
    Tester
    -0.06
    бу
    -0.06
    POSITIVE LOGITS
    (lat
    0.07
     designation
    0.07
    productive
    0.06
     ومن
    0.06
    (origin
    0.06
    _continue
    0.06
    り
    0.06
    Prices
    0.06
    _,
    0.06
    ,
    0.06
    Act Density 0.000%

    No Known Activations