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

    Neuronpedia

    INDEX
    Explanations

    button click action

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ה
    0.86
    و
    0.85
    ня
    0.84
    flashlight
    0.74
    itinéraire
    0.73
    oned
    0.72
    Toxic
    0.72
    Pharmac
    0.71
    ження
    0.70
    Medical
    0.70
    POSITIVE LOGITS
    rared
    0.77
     vesting
    0.75
     gossip
    0.72
    ᄑ
    0.72
     bipolar
    0.70
     Tô
    0.69
     Chí
    0.68
    ইতে
    0.68
    গাঁও
    0.66
     logros
    0.66
    Act Density 0.000%

    No Known Activations