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

    Neuronpedia

    INDEX
    Explanations

    Codenames, Book of Dead, uncharted Seas

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ك
    0.87
    ון
    0.78
    学生的
    0.72
     empieza
    0.72
    ция
    0.70
    的问题
    0.66
     gezeigt
    0.66
     rodzaj
    0.65
    تي
    0.64
     leh
    0.63
    POSITIVE LOGITS
    n
    0.73
     Monuments
    0.69
     Publications
    0.68
     Conference
    0.64
     अयोध्या
    0.64
     Istanbul
    0.63
     Corinthians
    0.62
    is
    0.61
     Psalms
    0.61
     Innovative
    0.61
    Act Density 0.000%

    No Known Activations