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

    Neuronpedia

    INDEX
    Explanations

    was

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    聽
    -0.06
     ought
    -0.06
    かけ
    -0.06
     dazu
    -0.06
     getSize
    -0.06
    ตร
    -0.06
    801
    -0.06
     outros
    -0.06
    126
    -0.06
     مذه
    -0.06
    POSITIVE LOGITS
    losures
    0.07
     communities
    0.07
     hospital
    0.06
     Grammy
    0.06
    management
    0.06
    (buffer
    0.06
    xl
    0.06
    last
    0.06
     scholars
    0.06
     measurement
    0.06
    Act Density 0.072%

    No Known Activations