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
    (offset
    -0.09
    Study
    -0.08
     mam
    -0.08
    902
    -0.08
    BC
    -0.07
    BW
    -0.07
    Project
    -0.07
    _OFFSET
    -0.07
     matk
    -0.07
    (link
    -0.07
    POSITIVE LOGITS
     правильно
    0.09
    0.09
     дроб
    0.08
     separar
    0.08
     strtolower
    0.08
     раньше
    0.08
     convention
    0.08
     مخکې
    0.08
     jealous
    0.08
    -за
    0.08
    Act Density 0.000%
    No Known Activations