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

    Neuronpedia

    INDEX
    Explanations

    until and endpoints

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     contains
    0.37
     was
    0.36
    )
    0.36
    に
    0.36
     doesn
    0.36
     př
    0.35
     birthplace
    0.35
    な
    0.34
    ),
    0.34
     contrôler
    0.34
    POSITIVE LOGITS
    until
    0.53
    Until
    0.51
     Until
    0.48
     until
    0.48
    直到
    0.46
    有一天
    0.45
     ድረስ
    0.45
    直至
    0.45
    为止
    0.43
     конца
    0.43
    Act Density 0.007%

    No Known Activations