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

    Neuronpedia

    INDEX
    Explanations

    intervening only

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     missão
    0.45
     मधुमेह
    0.42
    उचर
    0.41
     মিশন
    0.41
     vergang
    0.41
     decreed
    0.41
    ደበ
    0.40
     worshipped
    0.40
     choirs
    0.40
    쭤
    0.40
    POSITIVE LOGITS
    car
    0.42
     carico
    0.42
    endo
    0.41
    ho
    0.40
    Bob
    0.40
     Cs
    0.40
    or
    0.39
    o
    0.39
    IM
    0.38
    Adapt
    0.38
    Act Density 0.000%

    No Known Activations