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

    Neuronpedia

    INDEX
    Explanations

    modelcode models services controllers helpers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    erne
    0.96
    الصف
    0.95
    gallant
    0.88
     Développement
    0.88
    വന
    0.87
    에서는
    0.86
     Commerce
    0.86
    豳
    0.85
     शरी
    0.84
    വൃ
    0.84
    POSITIVE LOGITS
     model
    0.91
     exception
    0.88
    listener
    0.80
    model
    0.79
     utility
    0.73
     models
    0.71
     utils
    0.70
     exceptions
    0.68
    utils
    0.66
    exception
    0.66
    Act Density 0.022%

    No Known Activations