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

    Neuronpedia

    INDEX
    Explanations

    subtypes/types

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     مرکزی
    -0.08
     obvious
    -0.07
    columns
    -0.07
     河
    -0.07
     فعال
    -0.07
     اختیار
    -0.06
    ир
    -0.06
    ,['
    -0.06
    ==============↵
    -0.06
    .»
    -0.06
    POSITIVE LOGITS
     subtype
    0.10
    sc
    0.06
    Č
    0.06
     filib
    0.06
    .Singleton
    0.06
     双
    0.06
    (","
    0.06
    atype
    0.06
     resizing
    0.06
     Mockito
    0.06
    Act Density 0.003%

    No Known Activations