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

    Neuronpedia

    INDEX
    Explanations

    header, head, grid

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ल
    2.13
     tortillas
    1.92
    ю
    1.87
    Rite
    1.86
    ωσ
    1.86
     gotta
    1.84
    ات
    1.81
     persone
    1.79
    сколько
    1.78
     surgi
    1.76
    POSITIVE LOGITS
    فضل
    2.05
     Originally
    1.91
    >-->
    1.91
    ようやく
    1.80
    ../../
    1.74
    ્ઞ
    1.73
    鹉
    1.73
    ⁩
    1.71
    haba
    1.71
    chelon
    1.69
    Act Density 0.014%

    No Known Activations