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

    Neuronpedia

    INDEX
    Explanations

    Center name

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ième
    1.73
    нди
    1.64
    ن
    1.63
    naj
    1.58
    ت
    1.57
    دين
    1.55
    nij
    1.55
    ار
    1.53
    الس
    1.49
    sı
    1.48
    POSITIVE LOGITS
    که
    1.57
     ordem
    1.31
     декабря
    1.30
    於是
    1.28
     αλλά
    1.27
    quele
    1.26
     Grazie
    1.26
     ולא
    1.24
     напряжения
    1.24
    thia
    1.23
    Act Density 0.003%

    No Known Activations