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

    Neuronpedia

    INDEX
    Explanations

    rights and conditions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    י
    0.86
     október
    0.83
    ﯽ
    0.82
     israel
    0.80
     بِ
    0.79
    俩
    0.78
     inflammation
    0.77
    曛
    0.77
     dalej
    0.75
     کب
    0.75
    POSITIVE LOGITS
    Elements
    0.85
     práticas
    0.82
    phones
    0.79
    прави
    0.79
    prav
    0.78
    ess
    0.76
     панели
    0.76
    Families
    0.74
     chiaro
    0.72
    SAP
    0.71
    Act Density 0.000%

    No Known Activations