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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    /dist
    -0.07
    imid
    -0.07
     Leaves
    -0.07
    ZONE
    -0.07
    رضى
    -0.07
     Drag
    -0.06
    Disp
    -0.06
    �
    -0.06
    Sha
    -0.06
     Tobacco
    -0.06
    POSITIVE LOGITS
    パパ
    0.08
    บาง
    0.07
    之战
    0.07
    &M
    0.06
    锏
    0.06
    颚
    0.06
    出轨
    0.06
    ༎
    0.06
    cron
    0.06
    >equals
    0.06
    Act Density 0.033%

    No Known Activations