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

    Neuronpedia

    INDEX
    Explanations

    sampling

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     эксплуата
    -0.07
     erectile
    -0.07
     mezun
    -0.07
     proves
    -0.06
    SCRIPTOR
    -0.06
    企业
    -0.06
    лата
    -0.06
    しない
    -0.06
    证明
    -0.06
     хочу
    -0.06
    POSITIVE LOGITS
     sampling
    0.12
     Sampling
    0.10
    Sampling
    0.08
     sampled
    0.08
     Sammy
    0.08
     Tam
    0.07
     sampler
    0.07
    (handler
    0.07
    Padding
    0.07
    .av
    0.07
    Act Density 0.003%

    No Known Activations