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

    Neuronpedia

    INDEX
    Explanations

    frost on the ground, blowout

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    tır
    1.95
    ت
    1.87
    र
    1.86
    ം
    1.77
    ம்
    1.74
    𝘁
    1.74
    ์
    1.73
    zelfde
    1.67
    ו
    1.65
    i
    1.64
    POSITIVE LOGITS
     tions
    1.57
     δεν
    1.57
     Repairs
    1.46
     tion
    1.45
     plumbers
    1.44
    saver
    1.44
     perks
    1.42
     ovvero
    1.42
     linemen
    1.41
     smell
    1.40
    Act Density 0.217%

    No Known Activations