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

    Neuronpedia

    INDEX
    Explanations

    that

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     gev
    -0.08
    ELS
    -0.08
     ללמוד
    -0.07
     genom
    -0.07
     clusters
    -0.07
    沌
    -0.07
    Domains
    -0.07
     материалов
    -0.07
    打着
    -0.07
    SOFTWARE
    -0.07
    POSITIVE LOGITS
    .ActionBar
    0.07
    buf
    0.06
    拉动
    0.06
    쉿
    0.06
     dropped
    0.06
    agement
    0.06
    set
    0.06
    nage
    0.06
    쟀
    0.06
    ute
    0.06
    Act Density 0.002%

    No Known Activations