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

    Neuronpedia

    INDEX
    Explanations

    example usage, documentation comments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    a
    0.52
    folders
    0.50
     for
    0.48
     captured
    0.48
    t
    0.48
    the
    0.48
     a
    0.48
    ছে
    0.47
     développ
    0.47
     calibrate
    0.46
    POSITIVE LOGITS
    ح
    0.55
    える
    0.51
    izamos
    0.49
    在
    0.48
    ى
    0.48
     stärker
    0.47
    ీ
    0.43
    輿
    0.43
    ع
    0.42
    由于
    0.42
    Act Density 0.001%

    No Known Activations