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

    Neuronpedia

    INDEX
    Explanations

    code/technical language

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     AP
    -0.07
    Selector
    -0.07
    ентами
    -0.07
    ザ
    -0.07
     Humans
    -0.07
     Kota
    -0.07
    nf
    -0.07
     أس
    -0.07
    angi
    -0.06
    ılıp
    -0.06
    POSITIVE LOGITS
     Meat
    0.07
     tomb
    0.06
    ("(%
    0.06
     spikes
    0.06
     مواط
    0.06
    :@"
    0.06
     міг
    0.06
     Indeed
    0.06
     daycare
    0.06
     将
    0.06
    Act Density 0.000%

    No Known Activations