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

    Neuronpedia

    INDEX
    Explanations

    apache libraries

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Net
    0.44
    Consumer
    0.43
    ActionListener
    0.39
     MPM
    0.38
    RMS
    0.38
    incu
    0.38
    GIS
    0.37
     Mapa
    0.37
    自带
    0.36
     Consumer
    0.36
    POSITIVE LOGITS
     allah
    0.44
     pulley
    0.42
    ಲೆ
    0.41
     october
    0.40
     secreto
    0.39
     carré
    0.38
    సై
    0.38
    padding
    0.38
     ignoreString
    0.37
     secre
    0.37
    Act Density 0.000%

    No Known Activations