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

    Neuronpedia

    INDEX
    Explanations

    say ")" or punctuation

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    d
    -0.07
    J
    -0.07
     (>
    -0.06
     Чтобы
    -0.06
     nga
    -0.06
    ulumi
    -0.06
     carved
    -0.06
     права
    -0.06
    credible
    -0.06
    ोई
    -0.06
    POSITIVE LOGITS
    .purchase
    0.06
    (room
    0.06
     elé
    0.06
    .Unsupported
    0.06
     Prop
    0.06
     vô
    0.06
     retrieving
    0.06
     буд
    0.06
     chương
    0.06
     actionTypes
    0.06
    Act Density 0.047%

    No Known Activations