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

    Neuronpedia

    INDEX
    Explanations

    holding deposits

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ../
    0.74
     (/
    0.73
    .}\
    0.72
    }\
    0.68
    }(\
    0.66
    }(
    0.65
    ()\
    0.63
    blueprint
    0.63
     फिल्
    0.63
     dihap
    0.62
    POSITIVE LOGITS
    금을
    0.85
     currency
    0.83
     امتحان
    0.80
    რივი
    0.80
     currencies
    0.80
    rosc
    0.79
    تع
    0.78
    ське
    0.78
    vu
    0.78
    支付
    0.78
    Act Density 0.002%

    No Known Activations