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

    Neuronpedia

    INDEX
    Explanations

    formal letter formatting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     November
    0.59
     December
    0.53
     February
    0.52
     January
    0.50
     September
    0.49
     April
    0.48
     July
    0.48
     March
    0.48
     October
    0.48
     Oktober
    0.47
    POSITIVE LOGITS
     updateConfirm
    0.46
    ܬ
    0.46
    ତ୍
    0.45
     givenChar
    0.41
     matchList
    0.40
     valuation
    0.40
    Ղ
    0.39
     encouragement
    0.38
    টর
    0.38
     slits
    0.38
    Act Density 0.029%

    No Known Activations