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

    Neuronpedia

    INDEX
    Explanations

    self. attribute/method access

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    𝙊
    1.44
    𝙇
    1.39
    $;
    1.36
     borrar
    1.31
     brut
    1.30
     inad
    1.29
    Neben
    1.28
     medit
    1.27
    ³.
    1.23
     Grâce
    1.22
    POSITIVE LOGITS
    ت
    2.10
    a
    2.03
    an
    1.77
    ம்
    1.58
    ைப்
    1.54
    т
    1.54
    iye
    1.53
    aient
    1.52
    sr
    1.45
    es
    1.41
    Act Density 0.025%

    No Known Activations