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

    Neuronpedia

    INDEX
    Explanations

    programming

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     devuelve
    -0.08
    .Direction
    -0.06
     harga
    -0.06
    .Invariant
    -0.06
     Hz
    -0.06
     DialogResult
    -0.06
    (obs
    -0.06
     ايران
    -0.06
     гаран
    -0.06
    adresse
    -0.06
    POSITIVE LOGITS
    皇
    0.07
    bove
    0.07
     “…
    0.07
     ruling
    0.06
     "...
    0.06
     uniquely
    0.06
    ��
    0.06
     Tradition
    0.06
     occupation
    0.06
     unix
    0.06
    Act Density 0.080%

    No Known Activations