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

    Neuronpedia

    INDEX
    Explanations

    resume writing tasks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    $('#
    3.05
     fact
    2.75
    sb
    2.73
    sf
    2.67
    ात
    2.56
    ICAL
    2.50
    liners
    2.48
    nin
    2.48
    घव
    2.47
    iaal
    2.46
    POSITIVE LOGITS
    ৪
    3.15
    આ
    3.09
     yra
    3.07
    м
    3.04
    는
    2.84
    ৫
    2.79
    <unused1873>
    2.76
     windings
    2.72
    에
    2.68
    ن
    2.67
    Act Density 0.021%

    No Known Activations