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

    Neuronpedia

    INDEX
    Explanations

    "very" followed by descriptive word

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    는
    0.30
     Many
    0.28
    ۔
    0.28
     namespaces
    0.27
    ：
    0.27
    ().
    0.26
    IONS
    0.26
     虽然
    0.26
    ።
    0.26
     mappings
    0.26
    POSITIVE LOGITS
    на
    0.32
     hospitable
    0.28
    ד
    0.28
     pricey
    0.26
     sayıda
    0.26
    注重
    0.26
    gelijk
    0.26
     fazla
    0.26
     lucrative
    0.25
    leştir
    0.25
    Act Density 0.571%

    No Known Activations