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

    Neuronpedia

    INDEX
    Explanations

    hypothetical statements and possibilities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    or
    1.11
    el
    0.87
    ра
    0.82
    덜
    0.78
    至於
    0.77
     columnspan
    0.77
    ri
    0.77
    至于
    0.75
    Д
    0.75
    ي
    0.75
    POSITIVE LOGITS
    Buscar
    0.86
    本発明
    0.85
     مردم
    0.83
     spoken
    0.76
    গর্
    0.76
     Wikiseite
    0.76
    是因為
    0.75
     resented
    0.75
     startled
    0.75
     राज्य
    0.75
    Act Density 0.133%

    No Known Activations