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

    Neuronpedia

    INDEX
    Explanations

    conditions and dependencies

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ὔ
    0.45
    RIER
    0.44
     proxies
    0.42
    toothpaste
    0.41
     ऑनर्स
    0.41
    \}$,
    0.40
    راعظم
    0.39
    guides
    0.39
    Riemann
    0.39
    質感
    0.39
    POSITIVE LOGITS
     stick
    0.48
     merge
    0.43
    જ
    0.43
     اه
    0.43
     mezcla
    0.42
     malos
    0.42
     إذ
    0.42
     stal
    0.42
     അവരുടെ
    0.41
    rez
    0.41
    Act Density 0.001%

    No Known Activations