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

    Neuronpedia

    INDEX
    Explanations

    integral from 0 to 1

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    জিওথের
    0.40
    {(-
    0.38
     Grosso
    0.38
    eteenth
    0.38
     OÜ
    0.38
    akeda
    0.37
    肪
    0.37
     Brigitte
    0.37
     വിവര
    0.37
     negozi
    0.36
    POSITIVE LOGITS
     interval
    0.56
    Interval
    0.52
     границы
    0.51
     Interval
    0.50
    intervals
    0.48
     limits
    0.48
     bounds
    0.47
    interval
    0.46
     límites
    0.46
    limits
    0.44
    Act Density 0.005%

    No Known Activations