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

    Neuronpedia

    INDEX
    Explanations

    json format

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     இல்லாமல்
    0.42
     سوال
    0.41
    杼
    0.40
     อะไร
    0.39
     નવા
    0.39
    शिता
    0.39
     گروه
    0.38
     ശക്ത
    0.38
     табы
    0.38
     મોટા
    0.38
    POSITIVE LOGITS
    ឹង
    0.43
     fric
    0.37
     overhe
    0.36
    并
    0.36
     commotion
    0.36
     receptacle
    0.36
     spaced
    0.35
     evenings
    0.35
     wich
    0.35
     Huxley
    0.35
    Act Density 0.044%

    No Known Activations