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

    Neuronpedia

    INDEX
    Explanations

    exponential growth and increases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ాలే
    0.39
    ังก์
    0.39
    ૌ
    0.39
     Satt
    0.38
     zej
    0.38
     Roan
    0.38
    রূপ
    0.37
     سلو
    0.37
     širo
    0.37
     توز
    0.37
    POSITIVE LOGITS
     exponentially
    0.66
     grows
    0.63
     accelerates
    0.52
     schneller
    0.50
    Grow
    0.49
     increases
    0.49
    compound
    0.48
     exponential
    0.48
    exponential
    0.48
     grew
    0.48
    Act Density 0.000%

    No Known Activations