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

    Neuronpedia

    INDEX
    Explanations

    accusations and legal consequences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     dilution
    0.41
     dryness
    0.40
     নির্ধারণ
    0.40
    ophora
    0.39
     unterscheiden
    0.38
     deterrent
    0.38
     douleur
    0.38
     mengingat
    0.38
     pijn
    0.38
     interlayer
    0.38
    POSITIVE LOGITS
    锒
    0.68
    会被
    0.68
     illegally
    0.66
    ถูก
    0.62
    遭到
    0.62
     violating
    0.62
     liable
    0.61
     violated
    0.61
    被人
    0.61
     knowingly
    0.60
    Act Density 0.010%

    No Known Activations