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

    Neuronpedia

    INDEX
    Explanations

    code delimiters

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     En
    -0.07
     alloys
    -0.06
     brand
    -0.06
     Zip
    -0.06
     드
    -0.06
     hookers
    -0.06
    	Map
    -0.06
    131
    -0.06
    界
    -0.06
     وأ
    -0.06
    POSITIVE LOGITS
    aneously
    0.07
     �
    0.06
     manuscripts
    0.06
    homepage
    0.06
     gs
    0.06
     Ré
    0.06
    existing
    0.06
    ridor
    0.06
    attempt
    0.06
    probability
    0.06
    Act Density 0.029%

    No Known Activations