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

    Neuronpedia

    INDEX
    Explanations

    Affirmation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    培养
    -0.07
     Fields
    -0.07
     Center
    -0.07
     fines
    -0.07
    	results
    -0.07
    尥
    -0.07
     rouge
    -0.07
    balls
    -0.07
    binations
    -0.06
     caractère
    -0.06
    POSITIVE LOGITS
    .UTF
    0.07
     Prefix
    0.07
    ឆ
    0.07
    耜
    0.07
    腑
    0.07
    .');
↵
    0.07
     />,↵
    0.06
     ferm
    0.06
     quốc
    0.06
    פיר
    0.06
    Act Density 0.040%

    No Known Activations