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

    Neuronpedia

    INDEX
    Explanations

    font-size

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    erdale
    0.65
    ahiye
    0.64
    âm
    0.64
    érieure
    0.64
    داً
    0.63
    PathOf
    0.61
    ámicas
    0.61
    elom
    0.61
    ürn
    0.60
     Classifier
    0.60
    POSITIVE LOGITS
     including
    1.57
     which
    1.44
    including
    1.41
     you
    1.32
    which
    1.30
     incluindo
    1.25
     especially
    1.24
     incluyendo
    1.23
     waardoor
    1.23
     we
    1.22
    Act Density 0.004%

    No Known Activations