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

    Neuronpedia

    INDEX
    Explanations

    new or based on

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     စ
    0.42
    ၆
    0.42
     możliwość
    0.41
     शिकारी
    0.40
     கை
    0.39
    }}}=
    0.39
     willingly
    0.39
    壹章
    0.39
     വ്യക്ത
    0.39
     ሂደት
    0.39
    POSITIVE LOGITS
    '
    0.50
     nuevo
    0.49
     top
    0.47
     brom
    0.46
     new
    0.46
     них
    0.46
    的新
    0.46
    새
    0.46
     the
    0.45
    新的
    0.45
    Act Density 0.001%

    No Known Activations