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

    Neuronpedia

    INDEX
    Explanations

    non-alphanumeric characters and symbols

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Investor
    0.41
    ctree
    0.38
     Evernote
    0.38
     Coating
    0.38
    ത
    0.37
    JPEG
    0.37
     RGB
    0.37
    GEO
    0.36
    जगी
    0.36
     C
    0.36
    POSITIVE LOGITS
    もなく
    0.38
    ɾ
    0.35
    ゐ
    0.33
     ٿ
    0.32
    的基础上
    0.32
    不对
    0.32
     culminated
    0.32
    щины
    0.31
     davantage
    0.31
    ിയാണ്
    0.31
    Act Density 0.011%

    No Known Activations