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

    Neuronpedia

    INDEX
    Explanations

    closing tag keywords

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ouncing
    0.39
    собен
    0.38
    魏
    0.38
    帳
    0.38
    োর
    0.37
    ESSIONS
    0.37
     નક્કી
    0.37
    蕊
    0.36
    使其
    0.36
    确保
    0.36
    POSITIVE LOGITS
     high
    0.44
    घन
    0.40
     albeit
    0.39
     lanyard
    0.39
     Furthermore
    0.38
     ringan
    0.38
     exuber
    0.38
    豊富な
    0.38
     furthermore
    0.37
     විශ
    0.37
    Act Density 0.022%

    No Known Activations