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

    Neuronpedia

    INDEX
    Explanations

    react component props

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    EXECUT
    0.82
    }$)
    0.75
     beteiligt
    0.75
    Ⴌ
    0.74
    }$).
    0.73
     upright
    0.73
    зидент
    0.72
     ELLE
    0.72
     mx
    0.71
    빡
    0.71
    POSITIVE LOGITS
    hes
    0.83
     tovább
    0.82
    onavírus
    0.82
    нти
    0.80
    سون
    0.80
    iella
    0.78
    y
    0.78
    ições
    0.77
    yun
    0.76
    轉
    0.76
    Act Density 0.001%

    No Known Activations