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

    Neuronpedia

    INDEX
    Explanations

    dividing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .car
    -0.08
     modelo
    -0.07
    @dynamic
    -0.07
     startling
    -0.06
     dazzling
    -0.06
     engaging
    -0.06
     lap
    -0.06
    those
    -0.06
    .gender
    -0.06
     '/../
    -0.06
    POSITIVE LOGITS
    错误
    0.07
    449
    0.07
     verdict
    0.06
    ясь
    0.06
     divide
    0.06
    的事情
    0.06
    mun
    0.06
     perpetrated
    0.06
    orrar
    0.06
    expiry
    0.06
    Act Density 0.029%

    No Known Activations