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

    Neuronpedia

    INDEX
    Explanations

    command line flags and configuration

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ಸಂಧಿ
    0.53
    dengan
    0.47
    announce
    0.46
     سنة
    0.46
     მხოლოდ
    0.46
     فہرست
    0.46
     gesprek
    0.46
    ವಾರ
    0.45
    棗
    0.45
    ポルト
    0.45
    POSITIVE LOGITS
     column
    0.48
     Column
    0.46
    രിച്ച
    0.46
     $\
    0.43
     artificial
    0.43
     height
    0.42
     high
    0.41
     Ho
    0.40
    PushMatrix
    0.40
     $(
    0.40
    Act Density 0.000%

    No Known Activations