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

    Neuronpedia

    INDEX
    Explanations

    black

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    _
    1.40
    ع
    1.29
    ول
    1.20
    らの
    1.16
    いを
    1.15
    控股
    1.09
    H
    1.08
    ಾ
    1.08
    etin
    1.07
    J
    1.07
    POSITIVE LOGITS
     toil
    1.15
     texture
    1.10
     Это
    1.09
     exper
    1.08
     thwarted
    1.07
     advertisements
    1.05
     Peki
    1.05
     This
    1.04
     Tapi
    1.03
     Chargers
    1.03
    Act Density 0.177%

    No Known Activations