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

    Neuronpedia

    INDEX
    Explanations

    programming context

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ल
    0.73
    م
    0.72
     détermin
    0.69
     avert
    0.68
    স
    0.67
     Soak
    0.66
     focussing
    0.66
     disc
    0.65
     our
    0.64
     determining
    0.64
    POSITIVE LOGITS
    Morning
    0.82
    Auth
    0.81
     emoción
    0.81
    FBSDKSettings
    0.81
    그러나
    0.79
    Visa
    0.75
     писатель
    0.75
    Hrs
    0.75
    kę
    0.74
    Proceedings
    0.74
    Act Density 0.001%

    No Known Activations