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

    Neuronpedia

    INDEX
    Explanations

    intelligence sources

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Transparency
    0.41
     Dateien
    0.41
     Exposure
    0.40
    ifford
    0.40
     पारदर्शिता
    0.39
     security
    0.39
     Security
    0.39
     Sicherheit
    0.39
     Andromeda
    0.39
     安全
    0.38
    POSITIVE LOGITS
     source
    0.63
    Source
    0.63
     sources
    0.62
    sources
    0.62
    source
    0.61
     Sumber
    0.61
    SOURCE
    0.60
     fuente
    0.60
     Sources
    0.59
    SOURCES
    0.58
    Act Density 0.018%

    No Known Activations