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

    Neuronpedia

    INDEX
    Explanations

    structured collections of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    et
    0.79
     τη
    0.74
    звичай
    0.72
    oward
    0.70
    uren
    0.69
    it
    0.68
     rug
    0.67
     odred
    0.67
    ernsey
    0.67
     einen
    0.66
    POSITIVE LOGITS
     دوم
    0.86
     kaik
    0.81
     nowych
    0.81
    जेस्टिव
    0.81
    0.80
     các
    0.80
     случаев
    0.80
    ವೇ
    0.80
     sores
    0.79
     exposures
    0.79
    Act Density 0.171%

    No Known Activations