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

    Neuronpedia

    INDEX
    Explanations

    url encoding and parsing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    helium
    0.38
    下跌
    0.38
    dato
    0.37
    தியில்
    0.37
    かい
    0.36
     Defin
    0.36
    ğinin
    0.36
     définit
    0.36
    dataPro
    0.36
     апре
    0.35
    POSITIVE LOGITS
     URL
    1.02
     url
    0.99
    URL
    0.87
     URLs
    0.87
     urls
    0.87
     Url
    0.86
    url
    0.84
    Url
    0.74
    Urls
    0.70
    urls
    0.68
    Act Density 0.003%

    No Known Activations