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

    Neuronpedia

    INDEX
    Explanations

    code and programming constructs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     vena
    0.44
    Sheila
    0.40
    दयाल
    0.38
     peanut
    0.38
     cranberry
    0.37
     modulating
    0.37
     wel
    0.37
     pressed
    0.37
     PAH
    0.37
     чел
    0.37
    POSITIVE LOGITS
    it
    0.52
    if
    0.45
     renderEncoder
    0.44
    categorie
    0.43
    "(
    0.43
    }",
    0.42
    todo
    0.42
    elif
    0.42
    giv
    0.41
    temp
    0.38
    Act Density 0.033%

    No Known Activations