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

    Neuronpedia

    INDEX
    Explanations

    google search limitations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     вересня
    0.37
    PhotoMode
    0.37
     Petroleum
    0.36
    Sexy
    0.36
     ലേഖ
    0.35
    looped
    0.35
    Termination
    0.34
    Louise
    0.34
     promulgate
    0.34
     lộ
    0.33
    POSITIVE LOGITS
     Hagg
    0.46
     ib
    0.43
     හැකිය
    0.43
     काला
    0.40
     amarillo
    0.40
    वेदना
    0.39
    䚰
    0.39
     Sa
    0.38
     Hag
    0.38
     эт
    0.37
    Act Density 0.005%

    No Known Activations