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

    Neuronpedia

    INDEX
    Explanations

    named concepts or titles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    টি
    0.86
    v
    0.77
    णारा
    0.76
    いただけます
    0.73
    ν
    0.69
    ampil
    0.67
    ing
    0.67
    arder
    0.66
    ie
    0.66
    The
    0.65
    POSITIVE LOGITS
     Sake
    1.02
    ullivan
    1.00
     Choice
    0.97
     endorsement
    0.95
     insistence
    0.95
    s
    0.95
     decree
    0.94
     sake
    0.94
     Edge
    0.94
     Delight
    0.93
    Act Density 0.189%

    No Known Activations