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

    Neuronpedia

    INDEX
    Explanations

    place names and styles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     —
    -2.61
     они
    -2.52
     $-$
    -2.47
     halt
    -2.45
     --
    -2.28
     The
    -2.25
     или
    -2.20
    在她
    -2.20
     :/
    -2.14
    多くの
    -2.14
    POSITIVE LOGITS
    ｘ
    2.58
    噲
    2.44
     suisse
    2.41
    媖
    2.41
     Fichier
    2.34
    獁
    2.33
    趼
    2.31
    ｇ
    2.27
     signifikan
    2.22
    蝙
    2.22
    Act Density 0.004%

    No Known Activations