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

    Neuronpedia

    INDEX
    Explanations

    hand made or handcrafted

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ために
    0.89
    자
    0.86
     społec
    0.83
    나
    0.83
    ༠
    0.82
    larının
    0.82
    다
    0.78
    𝕖
    0.78
    기
    0.77
     problèmes
    0.75
    POSITIVE LOGITS
     (
    1.10
     Hand
    0.97
    ",
    0.91
     hand
    0.88
    Hand
    0.85
    W
    0.78
     Handmade
    0.73
    n
    0.72
    ,"
    0.71
     for
    0.70
    Act Density 0.011%

    No Known Activations