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

    Neuronpedia

    INDEX
    Explanations

    return None or false

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     nonzero
    1.22
    NotNull
    1.00
     TRUE
    0.98
    Truthy
    0.92
     True
    0.92
     nontrivial
    0.89
     Infinite
    0.87
     zeros
    0.87
     None
    0.87
     Null
    0.87
    POSITIVE LOGITS
    Elliott
    0.68
    ழை
    0.66
    夋
    0.65
    DialogInterface
    0.65
     Jangan
    0.64
    CollectionView
    0.63
    ฝ
    0.63
    essi
    0.63
     દ્વા
    0.62
    EventManager
    0.62
    Act Density 0.148%

    No Known Activations