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

    Neuronpedia

    INDEX
    Explanations

    ranges and measurements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ana
    0.50
    invert
    0.49
    inverse
    0.49
    frak
    0.49
     রাস
    0.48
    yce
    0.48
    '
    0.47
    indole
    0.47
    ukun
    0.46
     sages
    0.45
    POSITIVE LOGITS
     பேச்சு
    0.47
    セミナー
    0.46
     વધ
    0.46
    Semif
    0.44
     noticing
    0.44
    وید
    0.44
    Additionally
    0.43
    மேலும்
    0.43
     SAIL
    0.41
    বিস্ত
    0.41
    Act Density 0.000%

    No Known Activations