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
     Jing
    -0.07
    pleasant
    -0.07
    Positive
    -0.06
    時の
    -0.06
    Kel
    -0.06
     Damage
    -0.06
    ujícím
    -0.06
    ्य
    -0.06
    OfYear
    -0.06
     Poker
    -0.06
    POSITIVE LOGITS
     patients
    0.06
    }.↵
    0.06
    raises
    0.06
     onboard
    0.06
    ाभ
    0.06
     haircut
    0.06
     وجه
    0.06
     ----------↵
    0.06
     rushes
    0.05
    _bitmap
    0.05
    Act Density 0.030%

    No Known Activations