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

    Neuronpedia

    INDEX
    Explanations

    Pendahuluan section

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     carnage
    0.73
    illery
    0.68
    wesen
    0.66
     binoculars
    0.66
     bombé
    0.65
     oppressive
    0.65
     oppression
    0.64
     blowing
    0.63
     blown
    0.62
     उड़ा
    0.62
    POSITIVE LOGITS
    ABC
    0.67
    रेख
    0.64
     At
    0.61
    哟
    0.60
     الك
    0.58
     سپ
    0.58
    ○
    0.58
    Cou
    0.58
    スケジュール
    0.57
    disposing
    0.56
    Act Density 0.000%

    No Known Activations