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

    Neuronpedia

    INDEX
    Explanations

    using

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ρας
    -0.07
    พระ
    -0.07
    /Sub
    -0.06
    .toList
    -0.06
    protocols
    -0.06
    Story
    -0.06
    VERY
    -0.06
    _FLAGS
    -0.06
    운데
    -0.06
    _PROP
    -0.06
    POSITIVE LOGITS
    /co
    0.07
    'b
    0.07
     Olympic
    0.06
     evenly
    0.06
     SESSION
    0.06
    Inicio
    0.06
     juste
    0.06
     Arabic
    0.06
     tert
    0.06
    egrity
    0.06
    Act Density 0.046%

    No Known Activations