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

    Neuronpedia

    INDEX
    Explanations

    technical terms and descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     banal
    0.53
     generalization
    0.52
     unify
    0.49
     doubt
    0.46
     myeloid
    0.46
     broke
    0.46
     humanity
    0.46
     imply
    0.45
     doubts
    0.45
     planar
    0.45
    POSITIVE LOGITS
    ға
    0.44
    ائِ
    0.42
     उग
    0.41
     टेक्निकल
    0.40
    ôn
    0.40
    ầu
    0.40
    чү
    0.40
    údo
    0.40
    稍
    0.39
    鍱
    0.39
    Act Density 0.001%

    No Known Activations