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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     horrifying
    -0.07
     AttributeError
    -0.06
    fit
    -0.06
     plenty
    -0.06
    اساس
    -0.06
    forEach
    -0.06
     سنة
    -0.06
    document
    -0.06
    Dic
    -0.06
     compreh
    -0.06
    POSITIVE LOGITS
    chein
    0.07
     UAV
    0.07
     ACT
    0.07
     %%↵
    0.06
    ェ
    0.06
    .plan
    0.06
     ژوئ
    0.06
     Museum
    0.06
     Серг
    0.06
     mayores
    0.06
    Act Density 0.063%

    No Known Activations