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

    Neuronpedia

    INDEX
    Explanations

    web security

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    /big
    -0.07
    someone
    -0.07
     leaking
    -0.07
     Surprise
    -0.07
    _sg
    -0.06
     чуд
    -0.06
    「你
    -0.06
    ‌هایی
    -0.06
     noticias
    -0.06
    ,item
    -0.06
    POSITIVE LOGITS
     dresses
    0.07
    ресс
    0.06
     �
    0.06
     safeguards
    0.06
    (Clone
    0.06
     ];
    0.06
     rearr
    0.06
     protect
    0.06
     fret
    0.06
     protects
    0.06
    Act Density 0.020%

    No Known Activations