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

    Neuronpedia

    INDEX
    Explanations

    pretty much any/every/anything

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    2
    0.98
    EM
    0.87
    IN
    0.86
    a
    0.86
    P
    0.85
    AR
    0.84
     Diarsipkan
    0.82
    Amenities
    0.81
    0.81
     فائد
    0.80
    POSITIVE LOGITS
     on
    1.07
    ب
    1.04
    ુ
    0.95
    h
    0.91
    is
    0.88
    سی
    0.86
    ли
    0.83
    ق
    0.82
    ри
    0.77
     get
    0.75
    Act Density 0.000%

    No Known Activations