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

    Neuronpedia

    INDEX
    Explanations

    other

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    大会
    -0.07
     syrup
    -0.07
    	wg
    -0.06
    _LE
    -0.06
     encuentra
    -0.06
    供应
    -0.06
    .queue
    -0.06
    _star
    -0.06
    ادي
    -0.06
     nx
    -0.06
    POSITIVE LOGITS
    (kind
    0.07
     Verified
    0.06
     Afro
    0.06
     boş
    0.06
     Украї
    0.06
    하여
    0.06
     Lans
    0.06
     =>'
    0.06
     Hiring
    0.06
     teammates
    0.06
    Act Density 0.080%

    No Known Activations