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

    Neuronpedia

    INDEX
    Explanations

    obvious

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     CreateTagHelper
    -0.55
    ConstraintMaker
    -0.52
     Réponses
    -0.51
    KELEY
    -0.48
    最快更新
    -0.48
     PLWABN
    -0.47
     makeStyles
    -0.47
     الرياضيه
    -0.45
    irvana
    -0.45
    あれば
    -0.45
    POSITIVE LOGITS
     opérateurs
    0.62
     mecán
    0.58
     kaynağından
    0.57
     burbujas
    0.56
    слен
    0.54
     genoux
    0.54
     Passengers
    0.54
    ImageContext
    0.53
     nocturna
    0.53
     discussione
    0.52
    Act Density 0.001%

    No Known Activations