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

    Neuronpedia

    INDEX
    Explanations

    disposable materials

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     캐
    0.47
    ไหล
    0.46
    เชสเตอร์
    0.42
     bege
    0.41
     玄
    0.41
     маги
    0.41
    浼
    0.41
     रुच
    0.40
     кван
    0.40
    vercel
    0.40
    POSITIVE LOGITS
     Disposable
    0.43
     purchasing
    0.43
     Purchasing
    0.43
     holistic
    0.40
     disposable
    0.40
     forms
    0.39
     relative
    0.39
     radical
    0.38
    aments
    0.38
     troubled
    0.38
    Act Density 0.001%

    No Known Activations