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

    Neuronpedia

    INDEX
    Explanations

    machine learning concepts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Enabled
    -0.08
    モ
    -0.07
     chăm
    -0.07
    ☹
    -0.07
     Ans
    -0.07
    被誉
    -0.06
    �
    -0.06
    ﾉ
    -0.06
    🐑
    -0.06
     GetData
    -0.06
    POSITIVE LOGITS
     Evaluation
    0.08
    行政处罚
    0.07
    hospital
    0.07
    district
    0.07
    hart
    0.07
    Consult
    0.07
    定向
    0.07
     wäre
    0.07
     Direction
    0.07
    /alert
    0.07
    Act Density 0.022%

    No Known Activations