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

    Neuronpedia

    INDEX
    Explanations

    Research reporting

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    แผน
    -0.07
     데
    -0.07
    ้าส
    -0.06
     จ
    -0.06
     Esto
    -0.06
    과정
    -0.06
     créer
    -0.06
    922
    -0.06
    きた
    -0.06
     Cord
    -0.06
    POSITIVE LOGITS
    baş
    0.07
    _HAND
    0.07
    Candidates
    0.06
    сих
    0.06
     amended
    0.06
    (_,
    0.06
    verbatim
    0.06
    emption
    0.06
     भग
    0.06
    @Enable
    0.06
    Act Density 0.507%

    No Known Activations