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

    Neuronpedia

    INDEX
    Explanations

    violence and abuse

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ر
    1.07
    か
    0.99
    د
    0.97
    ع
    0.96
    ik
    0.94
    з
    0.92
    其他
    0.89
    er
    0.85
    с
    0.85
    el
    0.81
    POSITIVE LOGITS
     whatnot
    1.13
    romeda
    0.78
    radiative
    0.75
     Subsidi
    0.72
     nanofibers
    0.71
     biofilms
    0.70
     inextricably
    0.66
     goddesses
    0.65
     figuratively
    0.65
     blockchains
    0.64
    Act Density 1.989%

    No Known Activations