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

    Neuronpedia

    INDEX
    Explanations

    technical computing annotation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    The
    0.77
    l
    0.70
    r
    0.69
    고
    0.63
    as
    0.62
    one
    0.61
    to
    0.61
    the
    0.61
    ell
    0.58
    rag
    0.57
    POSITIVE LOGITS
     yaşam
    0.75
     pouquinho
    0.66
    탉
    0.59
    ką
    0.59
     overcrow
    0.59
     வசன
    0.58
     filmpje
    0.58
    ાર્થી
    0.57
    ccak
    0.57
    녕하십니까
    0.56
    Act Density 0.000%

    No Known Activations