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

    Neuronpedia

    INDEX
    Explanations

    hate and dislike

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     चिंता
    0.77
     preocupación
    0.73
     préoccup
    0.73
     preocup
    0.71
     Tham
    0.69
     táo
    0.68
    显得
    0.67
    肩膀
    0.67
    铤
    0.66
     concerns
    0.66
    POSITIVE LOGITS
     hate
    3.05
     hatred
    3.03
     dislike
    2.99
     hating
    2.91
     hated
    2.88
     hates
    2.86
     ненави
    2.67
     Hate
    2.66
     disliked
    2.59
     despise
    2.58
    Act Density 0.221%

    No Known Activations