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

    Neuronpedia

    INDEX
    Explanations

    and

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Amendments
    -0.07
    Krist
    -0.07
    女神
    -0.07
    �
    -0.07
     Cic
    -0.06
    AMPL
    -0.06
     plastic
    -0.06
    rieb
    -0.06
    .JSONObject
    -0.06
     Iss
    -0.06
    POSITIVE LOGITS
    epy
    0.07
    effects
    0.07
     الحقيقي
    0.07
     whipped
    0.07
    瘌
    0.07
    ивается
    0.07
    ações
    0.06
    もう
    0.06
    שים
    0.06
    Linear
    0.06
    Act Density 0.009%

    No Known Activations