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

    Neuronpedia

    INDEX
    Explanations

    enduring lasting concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    m
    0.74
    ";
    0.73
    es
    0.68
    ar
    0.64
    an
    0.63
    ");
    0.63
    ó
    0.63
     ejercicios
    0.62
    ed
    0.61
    ü
    0.61
    POSITIVE LOGITS
     durability
    0.77
    ष्णु
    0.75
     enduring
    0.73
     durable
    0.73
    hna
    0.73
     bền
    0.72
     महामारी
    0.71
     परंपरा
    0.70
     な
    0.68
     stronghold
    0.68
    Act Density 0.073%

    No Known Activations