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

    Neuronpedia

    INDEX
    Explanations

    governing equations, focused, lost

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    恶意
    0.80
     jeste
    0.77
     weder
    0.76
     nont
    0.75
     zakresie
    0.73
     ارزش
    0.69
     atypical
    0.69
     ው
    0.68
    ပြင်
    0.68
     unlike
    0.66
    POSITIVE LOGITS
    ,":
    0.87
    ™,
    0.87
    °,
    0.82
    ystick
    0.78
    kJ
    0.78
    ,"%
    0.78
    ,"$
    0.78
    (),"
    0.77
    lana
    0.77
    centi
    0.77
    Act Density 0.000%

    No Known Activations