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

    Neuronpedia

    INDEX
    Explanations

    code related discussions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     disob
    -0.06
    Guild
    -0.06
     Allows
    -0.06
    atern
    -0.06
    758
    -0.06
     ISA
    -0.06
    (home
    -0.06
     supper
    -0.06
     preprocessing
    -0.06
    овий
    -0.06
    POSITIVE LOGITS
    .profile
    0.07
    ivic
    0.07
     cesty
    0.06
    мець
    0.06
     인
    0.06
     المنت
    0.06
    Slash
    0.06
    /event
    0.06
    Head
    0.06
    _det
    0.06
    Act Density 0.770%

    No Known Activations