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

    Neuronpedia

    INDEX
    Explanations

    unique code or name

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     kttt
    0.59
    mito
    0.58
    multiply
    0.55
    ഗ്രഹ
    0.54
    planilla
    0.54
    replace
    0.53
    Multiply
    0.51
     نجي
    0.51
     学習
    0.51
    nummer
    0.50
    POSITIVE LOGITS
    '
    0.63
    ’
    0.57
    ↵
    0.54
    _
    0.50
     Date
    0.48
    ‌
    0.47
     prizes
    0.46
     broadcasts
    0.46
     adjourned
    0.46
     Blurred
    0.44
    Act Density 0.000%

    No Known Activations