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

    Neuronpedia

    INDEX
    Explanations

    Model

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     设
    -0.07
    -threatening
    -0.07
     Conversion
    -0.07
     Commit
    -0.06
    들과
    -0.06
     pushed
    -0.06
     SCREEN
    -0.06
    -final
    -0.06
    �
    -0.06
    (inner
    -0.06
    POSITIVE LOGITS
     populist
    0.07
     pís
    0.06
    líč
    0.06
    监听页面
    0.06
    >↵↵↵↵
    0.06
    isRequired
    0.06
     ---------------------------------------------------------------------------↵
    0.06
    optimize
    0.06
    stdin
    0.06
    skirts
    0.06
    Act Density 0.000%

    No Known Activations