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

    Neuronpedia

    INDEX
    Explanations

    API keys, authentication

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ]byte
    -0.06
    发布
    -0.06
    ジ
    -0.06
    .sign
    -0.06
     satisfying
    -0.06
    ونت
    -0.06
     sauces
    -0.06
     در
    -0.06
    dates
    -0.06
    dur
    -0.06
    POSITIVE LOGITS
     Seems
    0.06
     polym
    0.06
     expressive
    0.06
     finds
    0.06
     dps
    0.06
     demonstrators
    0.06
    yar
    0.06
    .Minimum
    0.06
     liar
    0.06
     broadcaster
    0.06
    Act Density 0.060%

    No Known Activations