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

    Neuronpedia

    INDEX
    Explanations

    museums

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Cardinal
    -0.07
     observe
    -0.06
     treasury
    -0.06
     кип
    -0.06
    OfWeek
    -0.06
     Hogwarts
    -0.06
     Stoke
    -0.06
    _tt
    -0.06
    .Item
    -0.06
     Florence
    -0.06
    POSITIVE LOGITS
    apple
    0.07
    Mid
    0.07
    replacement
    0.06
    /an
    0.06
     surrogate
    0.06
     plat
    0.06
    ।↵↵
    0.06
     مقاله
    0.06
    brain
    0.06
    autom
    0.06
    Act Density 0.087%

    No Known Activations