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

    Neuronpedia

    INDEX
    Explanations

    asking for details

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     dal
    0.88
     onge
    0.78
     dus
    0.73
     geg
    0.71
     bassa
    0.70
     mauvais
    0.69
     tuk
    0.69
     da
    0.69
     ges
    0.67
     hany
    0.67
    POSITIVE LOGITS
     What
    0.92
    What
    0.90
     How
    0.84
     what
    0.84
     是否
    0.82
     Presumably
    0.81
     Whats
    0.81
    是否有
    0.80
    どのような
    0.79
    How
    0.79
    Act Density 1.836%

    No Known Activations