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

    Neuronpedia

    INDEX
    Explanations

    `. punctuation or `gzip`

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Eight
    0.42
    十八
    0.42
    fireFlower
    0.40
    𝙳
    0.39
     eighteen
    0.39
    няў
    0.38
    VIII
    0.38
    Forty
    0.38
    ImportGroup
    0.37
    buttonLevel
    0.37
    POSITIVE LOGITS
     set
    0.48
    list
    0.43
    或
    0.41
     potentially
    0.40
     or
    0.39
    ದೇ
    0.38
    set
    0.37
     used
    0.37
     list
    0.37
     done
    0.36
    Act Density 0.013%

    No Known Activations