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

    Neuronpedia

    INDEX
    Explanations

    tripod shot

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    on
    1.35
    ミ
    1.23
    Ι
    1.16
    サ
    1.15
    )$
    1.14
    ၿ
    1.14
    ({\
    1.13
    シ
    1.09
    ၾ
    1.09
    ８
    1.08
    POSITIVE LOGITS
    ين
    1.41
    т
    1.32
    -
    1.20
    ید
    1.16
     הראש
    1.08
    ات
    1.04
    ة
    1.04
    ون
    1.03
    يك
    1.03
    iku
    1.00
    Act Density 0.000%

    No Known Activations