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

    Neuronpedia

    INDEX
    Explanations

    and

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     mins
    -0.07
     Thi
    -0.07
    第十
    -0.07
     Convert
    -0.07
    (chart
    -0.07
    teen
    -0.06
     denote
    -0.06
     shouts
    -0.06
     Breaking
    -0.06
     shift
    -0.06
    POSITIVE LOGITS
     Assembly
    0.09
    _SPECIAL
    0.08
    lee
    0.07
    _sy
    0.07
     usuarios
    0.07
     האחרונות
    0.07
    PLE
    0.07
    梳
    0.07
    meyeceği
    0.07
     SUB
    0.06
    Act Density 0.330%

    No Known Activations