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

    Neuronpedia

    INDEX
    Explanations

    Go `fmt` string literals

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    为空
    0.71
     sweet
    0.68
    될
    0.67
     pig
    0.67
     Bunny
    0.66
    筍
    0.66
    stream
    0.66
     स्म
    0.65
     мыш
    0.64
     eher
    0.63
    POSITIVE LOGITS
    अरविंद
    0.86
     annular
    0.84
    immediate
    0.84
     anodic
    0.81
    ệc
    0.80
    <unused71>
    0.80
    प्रभात
    0.79
     photospheric
    0.79
    နာ
    0.77
    ង្
    0.76
    Act Density 0.003%

    No Known Activations