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

    Neuronpedia

    INDEX
    Explanations

    speed

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     vp
    -0.08
    posição
    -0.08
    .bill
    -0.07
     hil
    -0.07
    孩童
    -0.07
    顽
    -0.07
     Neg
    -0.07
    sold
    -0.06
     gü
    -0.06
    KL
    -0.06
    POSITIVE LOGITS
    링
    0.07
    썹
    0.07
    ichen
    0.07
    thag
    0.07
    ibernate
    0.07
    -table
    0.07
    新模式
    0.07
    0.07
    ائن
    0.06
    _percentage
    0.06
    Act Density 0.016%

    No Known Activations