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

    Neuronpedia

    INDEX
    Explanations

    following, cations, enable, temp, tones

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     showing
    0.49
     redirected
    0.48
     fueling
    0.48
     augmenting
    0.48
    ア
    0.47
     prospective
    0.47
     fortified
    0.47
     redirection
    0.47
    واں
    0.47
     ungraded
    0.46
    POSITIVE LOGITS
    stek
    0.55
     კიდ
    0.52
    OGND
    0.50
    lambda
    0.48
    stech
    0.47
    sker
    0.46
     قصد
    0.46
    gten
    0.46
     技術
    0.45
     vielen
    0.45
    Act Density 0.000%

    No Known Activations