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

    Neuronpedia

    INDEX
    Explanations

    runners and Kings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    谪
    0.79
     ઘટ
    0.78
     DEJ
    0.77
     fenô
    0.77
    lovepoetry
    0.76
     домашних
    0.74
    ផលិត
    0.74
    parvec
    0.73
     poziomie
    0.72
     nulle
    0.72
    POSITIVE LOGITS
     पहिले
    0.83
    キング
    0.78
     Runners
    0.77
    keepers
    0.77
     onto
    0.73
     infect
    0.72
     runners
    0.71
     her
    0.70
     Kings
    0.70
    KING
    0.69
    Act Density 0.001%

    No Known Activations