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

    Neuronpedia

    INDEX
    Explanations

    let them know

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     要
    0.88
     いつ
    0.73
     ให้
    0.72
    我们要
    0.72
    えています
    0.71
     يجب
    0.70
    왠
    0.69
    णिज्य
    0.69
    要
    0.69
     llegando
    0.69
    POSITIVE LOGITS
     freely
    0.97
     dictate
    0.96
     into
    0.91
     freedom
    0.91
     roam
    0.87
     glimpse
    0.84
     loose
    0.83
     interpolate
    0.82
     flourish
    0.80
     свободно
    0.80
    Act Density 0.053%

    No Known Activations