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

    Neuronpedia

    INDEX
    Explanations

    alternative

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     sir
    0.45
     re
    0.41
    axy
    0.41
     openai
    0.40
     suspect
    0.40
     x
    0.39
    чном
    0.39
     பதி
    0.39
     bv
    0.39
     neuro
    0.38
    POSITIVE LOGITS
    headless
    0.49
    miri
    0.40
    Jade
    0.39
     муниципа
    0.38
    astaan
    0.38
    parking
    0.38
    总部
    0.38
     остается
    0.38
     остались
    0.38
    etään
    0.37
    Act Density 0.001%

    No Known Activations