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

    Neuronpedia

    INDEX
    Explanations

    all in all, in short

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     All
    0.61
     ALL
    0.56
    All
    0.55
     ऑल
    0.55
    Total
    0.49
     Entire
    0.47
     even
    0.47
     Total
    0.46
    getTotal
    0.43
    Even
    0.43
    POSITIVE LOGITS
     One
    0.54
     goodness
    0.50
     good
    0.45
     ಒಳ್ಳ
    0.45
    One
    0.43
     Favor
    0.43
    }^{+}=
    0.43
    ONE
    0.42
     ONE
    0.42
     GOOD
    0.41
    Act Density 0.001%

    No Known Activations