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

    Neuronpedia

    INDEX
    Explanations

    file -> sync project

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    taining
    0.88
     partake
    0.87
     oksid
    0.87
     Handsome
    0.86
     bersifat
    0.83
     stk
    0.81
     Spine
    0.81
     familiarize
    0.80
     DSP
    0.80
    nd
    0.80
    POSITIVE LOGITS
    حسن
    1.02
    el
    0.93
    enzi
    0.92
    aard
    0.89
    squa
    0.89
    AL
    0.87
    ALLE
    0.87
    ELINE
    0.87
    スケ
    0.83
    ची
    0.81
    Act Density 0.001%

    No Known Activations