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

    Neuronpedia

    INDEX
    Explanations

    From, PhD

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ुत
    -0.08
    /al
    -0.07
    �
    -0.07
    である
    -0.06
    Cerrar
    -0.06
     истории
    -0.06
    Tier
    -0.06
    Alex
    -0.06
    -human
    -0.06
    _CHANGE
    -0.06
    POSITIVE LOGITS
     Pick
    0.07
     作
    0.06
     disrupting
    0.06
     esteem
    0.06
     ort
    0.06
     starttime
    0.06
     Gn
    0.06
     χώ
    0.06
    χει
    0.06
    .Apply
    0.06
    Act Density 0.021%

    No Known Activations