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
     Their
    -0.07
     judge
    -0.07
     Polymer
    -0.06
    ạn
    -0.06
    \Notifications
    -0.06
     writings
    -0.06
     Lawyers
    -0.06
    qty
    -0.06
     everyone
    -0.06
    _now
    -0.06
    POSITIVE LOGITS
    {}".
    0.08
    anooga
    0.07
     strapon
    0.07
     Mädchen
    0.07
    amt
    0.07
    _grupo
    0.06
    ственно
    0.06
     İslam
    0.06
     przed
    0.06
    вей
    0.06
    Act Density 0.021%

    No Known Activations