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

    Neuronpedia

    INDEX
    Explanations

    word meanings

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    因地
    -0.07
     dictate
    -0.07
    آل
    -0.07
    👻
    -0.07
     כיום
    -0.07
    🇸
    -0.07
    _Select
    -0.07
    _builder
    -0.06
     endure
    -0.06
    岁月
    -0.06
    POSITIVE LOGITS
     Oczy
    0.06
    ornment
    0.06
    isNaN
    0.06
     deja
    0.06
     comm
    0.06
    .gallery
    0.06
     Large
    0.06
     spotted
    0.06
    embr
    0.06
    这对
    0.06
    Act Density 0.021%

    No Known Activations