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

    Neuronpedia

    INDEX
    Explanations

    rounded corners

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    假設
    0.58
    たとえば
    0.47
    Assume
    0.47
     tantôt
    0.46
     exemplu
    0.46
     Например
    0.44
    Assuming
    0.44
     exempel
    0.43
    例えば
    0.43
    账号
    0.43
    POSITIVE LOGITS
     say
    0.46
     Say
    0.42
     recommended
    0.40
     Buckley
    0.38
     AOS
    0.38
     corners
    0.38
     spaced
    0.37
     Schneider
    0.37
     Wentworth
    0.36
     рекомендуется
    0.36
    Act Density 0.000%

    No Known Activations