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

    Neuronpedia

    INDEX
    Explanations

    html link rel

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ーパー
    0.42
    Becker
    0.41
    aped
    0.39
    ived
    0.38
     Liebig
    0.37
    eries
    0.37
     coseno
    0.37
    野菜
    0.37
    Anth
    0.36
     végétation
    0.36
    POSITIVE LOGITS
     href
    2.08
    href
    1.97
    Href
    1.63
     HREF
    1.43
     rel
    1.12
     hre
    0.94
     xlink
    0.93
    rel
    0.90
     Rel
    0.86
     herring
    0.85
    Act Density 0.015%

    No Known Activations