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

    Neuronpedia

    INDEX
    Explanations

    Numbers and letters

    np_max-act · gemini-2.0-flash

    names for software applications in the context of graphical asset creation.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    いる
    -0.07
     Benchmark
    -0.07
     Rin
    -0.06
    outube
    -0.06
    成绩
    -0.06
     всех
    -0.06
     anticipation
    -0.06
     Examples
    -0.06
    THOOK
    -0.06
     Mata
    -0.06
    POSITIVE LOGITS
     лю
    0.07
    (proxy
    0.06
    ór
    0.06
    utor
    0.06
     Puerto
    0.06
    [F
    0.06
    ěst
    0.06
    ΙΛ
    0.06
     guint
    0.06
     표
    0.06
    Act Density 0.021%

    No Known Activations