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

    Neuronpedia

    INDEX
    Explanations

    Legal, official documents

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    はない
    -0.07
     thép
    -0.07
    ,__
    -0.07
     الأساسية
    -0.07
    &&!
    -0.07
    ത
    -0.07
    เธอ
    -0.07
     energia
    -0.06
     utilisateur
    -0.06
     adulti
    -0.06
    POSITIVE LOGITS
     initialValues
    0.07
    Գ
    0.07
    疫情防控
    0.07
    соб
    0.07
     Stamford
    0.07
    朔
    0.07
    Passwords
    0.07
    oard
    0.07
    澭
    0.07
    	rm
    0.07
    Act Density 0.039%

    No Known Activations