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

    Neuronpedia

    INDEX
    Explanations

    before

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Parser
    -0.07
     Ninh
    -0.07
     isinstance
    -0.06
    'options
    -0.06
    ดวก
    -0.06
     мереж
    -0.06
     Italia
    -0.06
    .getContext
    -0.06
     cil
    -0.06
     hvis
    -0.06
    POSITIVE LOGITS
    pla
    0.07
    ařilo
    0.07
    lıklı
    0.07
    allow
    0.07
    ilee
    0.07
     before
    0.07
    ीए
    0.06
     yüksel
    0.06
     surg
    0.06
    adratic
    0.06
    Act Density 0.018%

    No Known Activations