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

    Neuronpedia

    INDEX
    Explanations

    names from diverse languages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     firmware
    0.65
     nub
    0.61
     heed
    0.57
     fascia
    0.56
     mute
    0.55
     regex
    0.54
     endian
    0.54
     Firmware
    0.53
     seres
    0.53
     ember
    0.52
    POSITIVE LOGITS
    zcz
    0.67
    opol
    0.66
    kh
    0.65
    cheng
    0.64
    jean
    0.63
    jian
    0.63
    zh
    0.62
    sek
    0.62
    kre
    0.62
    ஹ
    0.62
    Act Density 0.131%

    No Known Activations