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

    Neuronpedia

    INDEX
    Explanations

    a or an beginning phrase

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ):
    0.29
     phon
    0.27
     추진
    0.25
    )?
    0.25
    )...
    0.24
     longer
    0.24
    which
    0.24
    )....
    0.24
    longer
    0.24
     IMO
    0.24
    POSITIVE LOGITS
     A
    0.28
    An
    0.27
     An
    0.25
     一个
    0.25
    a
    0.25
     gladly
    0.25
     оз
    0.24
    ンテ
    0.24
     Thankfully
    0.24
     Remarkably
    0.24
    Act Density 0.000%

    No Known Activations