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

    Neuronpedia

    INDEX
    Explanations

    describing specific examples

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    it
    1.10
    ov
    1.03
    وک
    1.01
     d
    0.96
    ah
    0.94
    ad
    0.92
    ag
    0.89
    <0x0D>
    0.89
     النا
    0.88
     t
    0.87
    POSITIVE LOGITS
     descricao
    1.50
     extravaganza
    1.47
     জন্য
    1.44
     rakh
    1.42
    𝓭
    1.41
    squared
    1.39
    descripcion
    1.39
    descricao
    1.37
    transferases
    1.36
    нің
    1.35
    Act Density 0.001%

    No Known Activations