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

    Neuronpedia

    INDEX
    Explanations

    code execution logic

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     None
    0.66
     prest
    0.65
     protection
    0.64
     hjälp
    0.63
     convi
    0.63
    怠
    0.61
    uss
    0.60
     result
    0.60
     PROTECTION
    0.58
    rict
    0.58
    POSITIVE LOGITS
    劏
    0.79
    Hor
    0.78
    ቴክ
    0.77
     कार्यकार
    0.76
    Kay
    0.75
    কির
    0.74
    Cancel
    0.74
     काउंसिल
    0.72
     Equival
    0.71
    Virtual
    0.71
    Act Density 0.046%

    No Known Activations