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

    Neuronpedia

    INDEX
    Explanations

    comma

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     preliminary
    -0.07
     Naughty
    -0.07
    _DOCUMENT
    -0.07
     conexao
    -0.07
     spoiled
    -0.07
    archical
    -0.07
    .sigmoid
    -0.07
     Wu
    -0.06
    keep
    -0.06
    uh
    -0.06
    POSITIVE LOGITS
     ange
    0.08
     Rolling
    0.07
    充分肯定
    0.07
    非常
    0.07
    Digest
    0.07
    アニ
    0.07
    ordon
    0.06
     ""↵
    0.06
    どんどん
    0.06
     stir
    0.06
    Act Density 0.011%

    No Known Activations