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

    Neuronpedia

    INDEX
    Explanations

    warnings and caution

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    phalodes
    1.30
    esthesia
    1.26
    ⅞
    1.18
    ά
    1.17
    BOUND
    1.09
     resol
    1.08
    getId
    1.06
    <0x99>
    1.06
     sne
    1.05
    weird
    1.04
    POSITIVE LOGITS
     cautioned
    1.62
     warnings
    1.34
    ภัย
    1.29
     cautionary
    1.27
     cautions
    1.26
    ن
    1.25
    廣場
    1.25
     Warnings
    1.16
     warning
    1.14
     caution
    1.12
    Act Density 0.054%

    No Known Activations