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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     carv
    -0.09
     perfiles
    -0.09
     cherchent
    -0.08
     perfil
    -0.07
    _query
    -0.07
     représentent
    -0.07
     profiling
    -0.07
    ിത്ത
    -0.07
     etc
    -0.07
     подходят
    -0.07
    POSITIVE LOGITS
    禁止
    0.14
     discour
    0.13
    prevent
    0.12
     запрещ
    0.12
     prevented
    0.12
     verhindert
    0.12
     restricting
    0.12
     enforced
    0.12
     empê
    0.12
     Restr
    0.12
    Act Density 0.008%

    No Known Activations