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

    Neuronpedia

    INDEX
    Explanations

    android xml code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ！（
    -1.25
    ！(
    -1.16
     even
    -1.15
    ！　
    -1.14
    ～。
    -1.10
    …！
    -1.09
     one
    -1.09
     because
    -1.08
    独特
    -1.08
     stellar
    -1.07
    POSITIVE LOGITS
     dreary
    1.30
     delightfully
    1.26
     этих
    1.24
     essas
    1.23
     boister
    1.23
     ™
    1.18
     AMAZING
    1.18
     predominantly
    1.18
    きち
    1.16
    鶫
    1.15
    Act Density 0.003%

    No Known Activations