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

    Neuronpedia

    INDEX
    Explanations

    spin-orbit coupling and workability

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    f
    0.95
    ר
    0.93
    z
    0.85
    ل
    0.82
    וג
    0.81
    ק
    0.80
    ורי
    0.79
    ץ
    0.77
     is
    0.73
    ል።
    0.73
    POSITIVE LOGITS
     μπορεί
    0.92
     extremamente
    0.92
    เป็น
    0.89
     estremamente
    0.86
     difíciles
    0.82
     ecclesiastical
    0.80
     étudiant
    0.78
     крайне
    0.76
     খুবই
    0.74
     έχουν
    0.73
    Act Density 0.003%

    No Known Activations