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

    Neuronpedia

    INDEX
    Explanations

    a

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ]}↵
    -0.07
     아닌
    -0.07
    Utc
    -0.07
    По
    -0.07
    된다
    -0.07
    !↵↵↵↵
    -0.07
     شوند
    -0.06
    以来
    -0.06
     Lv
    -0.06
     trustworthy
    -0.06
    POSITIVE LOGITS
    _world
    0.06
     Autos
    0.06
     McCartney
    0.06
    ANI
    0.06
    Wis
    0.06
    <Token
    0.06
     slur
    0.06
    ��取
    0.06
    cer
    0.06
     religious
    0.06
    Act Density 0.004%

    No Known Activations