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

    Neuronpedia

    INDEX
    Explanations

    fine mist and humidification

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     n
    0.70
    '
    0.69
    ’
    0.66
     a
    0.63
    :
    0.60
     y
    0.60
     changes
    0.59
     mesons
    0.57
     figurines
    0.56
     on
    0.55
    POSITIVE LOGITS
    في
    0.66
    و
    0.66
    ベ
    0.65
    Deux
    0.63
    اک
    0.63
    ده
    0.62
    ον
    0.62
    治
    0.62
    在北京
    0.61
    ۳
    0.61
    Act Density 0.001%

    No Known Activations