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

    Neuronpedia

    INDEX
    Explanations

    configuration files

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     freshness
    -0.07
     eliminate
    -0.07
    released
    -0.07
     chọn
    -0.07
    神州
    -0.07
     contestants
    -0.07
    مسرح
    -0.07
    גז
    -0.07
    ikes
    -0.06
    RID
    -0.06
    POSITIVE LOGITS
    dap
    0.07
    ,,,,
    0.07
    区间
    0.06
    较好的
    0.06
     המע
    0.06
     persecuted
    0.06
    -Aug
    0.06
     dialect
    0.06
    enus
    0.06
    对我
    0.06
    Act Density 0.009%

    No Known Activations