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

    Neuronpedia

    INDEX
    Explanations

    aspects of existing things

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     overturned
    0.84
    वायु
    0.81
     permanec
    0.81
     pensamiento
    0.81
    경기도
    0.80
     retracted
    0.80
     labile
    0.80
    涘
    0.79
     río
    0.77
     combate
    0.77
    POSITIVE LOGITS
    Ⅲ
    0.84
    tı
    0.82
    Subject
    0.74
    한편
    0.73
    tare
    0.73
    subj
    0.72
     brie
    0.72
    Older
    0.71
    Ⅱ
    0.71
    ExceptionHandler
    0.71
    Act Density 0.000%

    No Known Activations