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

    Neuronpedia

    INDEX
    Explanations

    mathematical calculation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     accompanied
    0.42
    ക്കാര
    0.39
    व्स
    0.38
     CORPOR
    0.36
    accompanied
    0.36
    Sad
    0.36
    ယ
    0.36
     gewisse
    0.35
     disturbing
    0.35
     anum
    0.35
    POSITIVE LOGITS
     Calculation
    0.57
     calculation
    0.53
     Calculations
    0.52
    calculation
    0.50
    Calculation
    0.48
     calculate
    0.47
     계산
    0.46
     Subtract
    0.45
    calculate
    0.45
    subtract
    0.44
    Act Density 0.055%

    No Known Activations