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

    Neuronpedia

    INDEX
    Explanations

    lists of names/titles

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    年来
    -0.08
    '])
    -0.08
    >Password
    -0.08
    "])
    -0.08
    asticsearch
    -0.08
    Таким
    -0.08
    -0.08
     alleine
    -0.08
     PHPUnit
    -0.08
     salari
    -0.07
    POSITIVE LOGITS
     worldly
    0.08
    av
    0.07
    ipta
    0.07
     omn
    0.07
     سوی
    0.07
    Charge
    0.07
     Infinity
    0.07
    ris
    0.07
     exponential
    0.07
    of
    0.07
    Act Density 0.023%
    No Known Activations