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

    Neuronpedia

    INDEX
    Explanations

    specific time period of Core offering

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    นะ
    0.83
     성
    0.79
    นั้น
    0.75
     idempot
    0.73
    ນ
    0.72
     الأد
    0.70
     شە
    0.70
     fortemente
    0.70
    นะคะ
    0.69
    甠
    0.69
    POSITIVE LOGITS
    вали
    0.77
    aita
    0.76
    igare
    0.73
    allar
    0.73
    itsa
    0.71
    稳定性
    0.69
    生涯
    0.68
    ering
    0.68
    TA
    0.67
    els
    0.67
    Act Density 0.030%

    No Known Activations