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

    Neuronpedia

    INDEX
    Explanations

    own safety filters, custom plugins, own dishes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    क
    1.21
    dür
    1.04
     inorder
    1.00
     i
    0.95
     o
    0.92
     c
    0.90
     oo
    0.89
     -
    0.89
     all
    0.89
     OCLC
    0.89
    POSITIVE LOGITS
    ל
    1.31
     таки
    1.20
    на
    1.15
     volition
    1.09
    લ
    1.02
    ار
    0.98
    こと
    0.98
    apeutics
    0.98
    ৯
    0.98
     लागि
    0.97
    Act Density 0.019%

    No Known Activations