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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    credentials
    -0.07
    deadline
    -0.07
     illicit
    -0.07
     Buffered
    -0.06
    .per
    -0.06
     landscapes
    -0.06
    adam
    -0.06
     Colour
    -0.06
    workflow
    -0.06
    edited
    -0.06
    POSITIVE LOGITS
     ăn
    0.07
     clan
    0.07
    ционной
    0.07
     apare
    0.07
    !"
    0.07
     آس
    0.06
    _ME
    0.06
    нему
    0.06
    rawing
    0.06
    IENTATION
    0.06
    Act Density 0.030%

    No Known Activations