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

    Neuronpedia

    INDEX
    Explanations

    in of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    chat
    -0.07
    isOk
    -0.07
    noun
    -0.07
     Determine
    -0.07
    smart
    -0.06
    _jet
    -0.06
     train
    -0.06
    ющим
    -0.06
    payload
    -0.06
    (fin
    -0.06
    POSITIVE LOGITS
     erotica
    0.07
     수강
    0.06
     Επι
    0.06
     Toronto
    0.06
     öl
    0.06
    υκ
    0.06
     in
    0.06
    股
    0.06
     익
    0.06
     Mississippi
    0.06
    Act Density 0.337%

    No Known Activations