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

    Neuronpedia

    INDEX
    Explanations

    summaries and technical explanations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -begin
    -0.07
    بوب
    -0.07
    evaluation
    -0.07
     pedal
    -0.07
     значит
    -0.06
    گار
    -0.06
    kills
    -0.06
    kie
    -0.06
    :D
    -0.06
    ,callback
    -0.06
    POSITIVE LOGITS
     sino
    0.07
     ngx
    0.07
    海外
    0.06
    到底
    0.06
     hopeful
    0.06
    提供
    0.06
    serter
    0.06
     уклад
    0.06
    ící
    0.06
    Matching
    0.06
    Act Density 0.179%

    No Known Activations