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

    Neuronpedia

    INDEX
    Explanations

    words starting with she

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     মুক্তিযুদ্ধের
    0.99
     אות
    0.90
    ियम
    0.87
    quartered
    0.85
    écut
    0.84
     TestBed
    0.84
     unaccount
    0.81
    🅽
    0.80
    屌
    0.80
     homeless
    0.80
    POSITIVE LOGITS
    e
    1.13
     herself
    0.95
    tl
    0.94
     citrate
    0.93
     điều
    0.92
     Jane
    0.90
    pher
    0.89
    eit
    0.85
    毕竟
    0.84
    tional
    0.84
    Act Density 0.003%

    No Known Activations