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

    Neuronpedia

    INDEX
    Explanations

    deep understanding

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     өл
    0.46
     Followers
    0.44
     pedagog
    0.43
     pedag
    0.43
     Gamble
    0.42
     educativas
    0.40
    etermin
    0.40
     anniversary
    0.40
     Ingles
    0.40
     pedagogical
    0.40
    POSITIVE LOGITS
    深
    0.77
    Deep
    0.75
    deep
    0.74
     глубо
    0.71
     깊
    0.68
     deep
    0.67
    깊
    0.63
    深度
    0.61
     derin
    0.61
     sâu
    0.57
    Act Density 0.000%

    No Known Activations