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

    Neuronpedia

    INDEX
    Explanations

    http

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     coupe
    -0.08
     onNext
    -0.07
    (rng
    -0.07
    _candidates
    -0.07
    חייב
    -0.07
    ublic
    -0.06
    ображен
    -0.06
    -chevron
    -0.06
     compl
    -0.06
    $options
    -0.06
    POSITIVE LOGITS
    极大的
    0.07
    olicit
    0.07
     Morph
    0.06
    "):↵
    0.06
    四项
    0.06
    .Hosting
    0.06
    放过
    0.06
    突击
    0.06
     DEVELO
    0.06
     plummet
    0.06
    Act Density 0.004%

    No Known Activations