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

    Neuronpedia

    INDEX
    Explanations

    lists structure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     givenChar
    0.45
    癀
    0.40
    FILENAME
    0.39
     pozwala
    0.39
     oportunidad
    0.38
    ණය
    0.38
     compromiso
    0.38
    OutputDir
    0.38
     riots
    0.38
     Discrimin
    0.37
    POSITIVE LOGITS
    view
    0.47
    back
    0.40
    ider
    0.40
    hens
    0.38
    apple
    0.38
    her
    0.38
    clad
    0.38
    Tg
    0.37
    ser
    0.37
    link
    0.37
    Act Density 0.000%

    No Known Activations