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

    Neuronpedia

    INDEX
    Explanations

    voting

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _sampler
    -0.07
    ，又
    -0.07
    又
    -0.06
    INSTANCE
    -0.06
    还有
    -0.06
     involve
    -0.06
    앙
    -0.06
     arresting
    -0.06
    안
    -0.06
     malaysia
    -0.06
    POSITIVE LOGITS
    sss
    0.08
    -hop
    0.07
     ذلك
    0.07
     kararı
    0.06
     cocaine
    0.06
    (problem
    0.06
    -Core
    0.06
     بیشتری
    0.06
     titre
    0.06
    onder
    0.06
    Act Density 0.006%

    No Known Activations