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

    Neuronpedia

    INDEX
    Explanations

    removal

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Sound
    -0.08
    Joe
    -0.07
    öst
    -0.07
     domina
    -0.07
    来讲
    -0.07
    otify
    -0.07
     Sonic
    -0.07
    pei
    -0.07
    _symbol
    -0.07
    /commons
    -0.07
    POSITIVE LOGITS
     retour
    0.08
    mad
    0.07
    电子邮件
    0.07
    �
    0.07
     renewal
    0.07
    素晴
    0.07
    พ
    0.07
    ])*
    0.07
     attachment
    0.07
     quyền
    0.07
    Act Density 0.019%

    No Known Activations