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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     افراد
    -0.07
    :UI
    -0.06
    #ad
    -0.06
     Kindle
    -0.06
    afür
    -0.06
     memiliki
    -0.06
    �
    -0.06
    NonNull
    -0.06
    ovable
    -0.06
     wird
    -0.06
    POSITIVE LOGITS
     of
    0.06
    ism
    0.06
     нег
    0.06
    _ini
    0.06
    selector
    0.06
    idf
    0.06
    CLASS
    0.06
    fine
    0.06
    ωδ
    0.06
    Κ
    0.06
    Act Density 0.012%

    No Known Activations