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

    Neuronpedia

    INDEX
    Explanations

    /html

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ٔ
    -0.07
    	Request
    -0.06
     Joseph
    -0.06
     kvp
    -0.06
     작품
    -0.06
     eing
    -0.06
    -ra
    -0.06
     حافظ
    -0.06
    outed
    -0.06
     Kam
    -0.06
    POSITIVE LOGITS
     �
    0.07
    	sd
    0.07
    (){}↵↵
    0.07
    окумент
    0.06
    assertTrue
    0.06
     />}↵
    0.06
     Dense
    0.06
    /disc
    0.06
     Precision
    0.06
     envelope
    0.06
    Act Density 0.001%

    No Known Activations