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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ственных
    -0.07
     Technician
    -0.07
    .prototype
    -0.07
    (Source
    -0.07
    .Option
    -0.07
     concert
    -0.06
    /trans
    -0.06
     Audience
    -0.06
    _quad
    -0.06
    Death
    -0.06
    POSITIVE LOGITS
     точно
    0.06
    ([('
    0.06
    ในร
    0.06
    Lemma
    0.06
     kể
    0.06
    خیص
    0.06
     voting
    0.06
     จะ
    0.06
    пор
    0.06
     Vac
    0.06
    Act Density 0.000%

    No Known Activations