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

    Neuronpedia

    INDEX
    Explanations

    scientific/technical descriptions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    一度
    -0.07
    리지
    -0.07
    :variables
    -0.07
     successes
    -0.07
     جوان
    -0.07
     Pleasant
    -0.07
     Amendments
    -0.07
    下
    -0.06
     زیر
    -0.06
     Vill
    -0.06
    POSITIVE LOGITS
    _SLAVE
    0.07
    567
    0.06
    .readAs
    0.06
    圭圭
    0.06
     keynote
    0.06
     ZERO
    0.06
     HVAC
    0.06
     Robin
    0.06
     dependency
    0.06
    ��
    0.05
    Act Density 0.238%

    No Known Activations