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

    Neuronpedia

    INDEX
    Explanations

    github.com and user mentions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     నొప్పి
    0.45
     AppModule
    0.44
     ಸಂಧಿ
    0.44
    🏚
    0.44
    옻
    0.41
    äude
    0.41
     Eqs
    0.41
     cavité
    0.40
     ಸಮಸ್ಯೆ
    0.40
    🤱
    0.40
    POSITIVE LOGITS
     john
    0.90
    j
    0.87
    david
    0.86
     Chris
    0.83
    john
    0.83
    chris
    0.82
     John
    0.80
     David
    0.79
     chris
    0.79
     j
    0.79
    Act Density 0.005%

    No Known Activations