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

    Neuronpedia

    INDEX
    Explanations

    who

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     خطر
    -0.07
    YRO
    -0.06
     sarcast
    -0.06
    tığ
    -0.06
    ================================================
    -0.06
     за
    -0.06
    起来
    -0.06
     charities
    -0.06
    face
    -0.06
    하
    -0.06
    POSITIVE LOGITS
     assort
    0.06
     CCS
    0.06
     Anat
    0.06
    thag
    0.06
    酒店
    0.06
    sol
    0.06
    }/#{
    0.06
     solar
    0.06
     ters
    0.06
    NSDate
    0.06
    Act Density 0.061%

    No Known Activations