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

    Neuronpedia

    INDEX
    Explanations

    how I or to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     loos
    0.43
     wanting
    0.41
     modific
    0.40
     poetic
    0.40
    니
    0.40
     GoPro
    0.38
     roulette
    0.38
     sightseeing
    0.38
     wondered
    0.38
    нець
    0.38
    POSITIVE LOGITS
    жен
    0.40
    ों
    0.38
     związ
    0.38
    >,
    0.38
    คุณ
    0.37
    masing
    0.36
    sière
    0.36
    ς
    0.36
    pyridazin
    0.36
    Tenemos
    0.36
    Act Density 0.827%

    No Known Activations