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

    Neuronpedia

    INDEX
    Explanations

    storage configurations, like to, willing to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ส
    0.40
     Renn
    0.39
     upper
    0.38
     Stet
    0.38
    '
    0.38
     '').
    0.38
    ス
    0.38
    quear
    0.38
     Mul
    0.37
     fossil
    0.37
    POSITIVE LOGITS
    न्छ
    0.48
    عيه
    0.48
    vmin
    0.47
     bởi
    0.46
    ிடம்
    0.44
    ≺
    0.43
    ɖ
    0.43
    ("%.
    0.43
    ゴルフクラブ
    0.43
    حدث
    0.43
    Act Density 0.008%

    No Known Activations