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

    Neuronpedia

    INDEX
    Explanations

    legal standards and judgements

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     parece
    -0.07
     forfeiture
    -0.07
    Equals
    -0.07
     Phase
    -0.06
     Ruth
    -0.06
    óż
    -0.06
    _integration
    -0.06
    ارت
    -0.06
     Spin
    -0.06
    �
    -0.06
    POSITIVE LOGITS
    <(),
    0.07
     plaintext
    0.07
    .opens
    0.06
    mercial
    0.06
    lify
    0.06
    ม
    0.06
     ASUS
    0.06
    >;
↵
    0.06
    ][:
    0.06
    .arange
    0.06
    Act Density 0.015%

    No Known Activations