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

    Neuronpedia

    INDEX
    Explanations

    rate

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     dign
    -0.07
    seconds
    -0.06
    OMP
    -0.06
    .bits
    -0.06
    <P
    -0.06
    unkt
    -0.06
    子的
    -0.06
    506
    -0.06
    adem
    -0.06
    调用
    -0.06
    POSITIVE LOGITS
    صول
    0.07
    �
    0.06
     lr
    0.06
    abol
    0.06
    ώς
    0.06
     hızla
    0.06
    bond
    0.06
     radicals
    0.06
    ":{"
    0.06
     Radical
    0.06
    Act Density 0.002%

    No Known Activations