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

    Neuronpedia

    INDEX
    Explanations

    index

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Tunisia
    -0.08
    titulo
    -0.07
    ussed
    -0.07
    _Search
    -0.07
    提问
    -0.07
     tích
    -0.07
     insulin
    -0.07
    (shift
    -0.07
    .descripcion
    -0.07
    .GetName
    -0.07
    POSITIVE LOGITS
    Ma
    0.08
     Stein
    0.07
    <|endoftext|>
    0.07
    :]↵
    0.07
     Con
    0.07
     rear
    0.07
     :]↵
    0.06
    Han
    0.06
     lab
    0.06
     he
    0.06
    Act Density 0.001%

    No Known Activations