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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Romanian
    -0.07
     삭제
    -0.07
    noch
    -0.07
    arus
    -0.07
     Gerry
    -0.06
    (LogLevel
    -0.06
     gang
    -0.06
    madığı
    -0.06
     thử
    -0.06
     Assoc
    -0.06
    POSITIVE LOGITS
    deserialize
    0.07
     TOD
    0.06
    erts
    0.06
    _tv
    0.06
     jasmine
    0.06
    Μ
    0.06
    encoding
    0.06
    ूरत
    0.06
    SON
    0.06
    _CAPACITY
    0.06
    Act Density 0.008%

    No Known Activations