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

    Neuronpedia

    INDEX
    Explanations

    graduation or graduated

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    魎
    1.26
     linewidth
    1.19
    šli
    1.18
     $*$
    1.15
    كم
    1.15
     overthrown
    1.14
    igheden
    1.11
     oxides
    1.09
     receivable
    1.08
     iframe
    1.08
    POSITIVE LOGITS
    <bos>
    1.24
     malos
    1.15
    ч
    1.13
    de
    1.11
     tõ
    1.05
     уж
    1.04
    шча
    1.04
    уч
    1.00
    ро
    0.99
    y
    0.99
    Act Density 0.017%

    No Known Activations