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

    Neuronpedia

    INDEX
    Explanations

    FastChat or chatbots

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ফোঁ
    0.49
     chemicals
    0.44
    স্তান
    0.43
     belong
    0.42
     abstracts
    0.42
     साबित
    0.41
     실험
    0.41
     comedians
    0.41
     آزمایش
    0.40
    質量
    0.40
    POSITIVE LOGITS
    cta
    0.45
    Personally
    0.44
    Miscellaneous
    0.44
    Initial
    0.41
    Cel
    0.40
     giường
    0.40
    Muito
    0.40
    Lire
    0.40
    lipper
    0.39
    阍
    0.39
    Act Density 0.001%

    No Known Activations