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

    Neuronpedia

    INDEX
    Explanations

    heritage site

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Dec
    0.77
    ões
    0.75
    neys
    0.75
    acharya
    0.73
    Charging
    0.73
    akrishna
    0.72
    Cop
    0.72
    ଛ
    0.71
    Parent
    0.70
    ungsver
    0.69
    POSITIVE LOGITS
     nugget
    0.90
    ょ
    0.74
    亿美元
    0.67
    अव
    0.66
     사건
    0.66
     infect
    0.65
     brushless
    0.63
    棧
    0.63
    }}$-
    0.60
    ^_
    0.60
    Act Density 0.012%

    No Known Activations