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

    Neuronpedia

    INDEX
    Explanations

    for

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	callback
    -0.09
     ie
    -0.08
    кет
    -0.08
     다시
    -0.08
     eas
    -0.08
     придется
    -0.08
     ehk
    -0.07
     callback
    -0.07
     rebound
    -0.07
     ị
    -0.07
    POSITIVE LOGITS
     विव
    0.09
     यदि
    0.08
    เมื่อ
    0.08
    ्यम
    0.08
    identified
    0.08
    Selected
    0.08
     возника
    0.08
     based
    0.08
    .Selected
    0.08
     thoughtfully
    0.07
    Act Density 0.112%

    No Known Activations