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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (old
    -0.06
     DID
    -0.06
    OL
    -0.06
     Owens
    -0.06
    -0.06
    经营
    -0.06
     surrogate
    -0.06
    primary
    -0.06
    �
    -0.06
     Opens
    -0.06
    POSITIVE LOGITS
     أمريكي
    0.07
    ###############################################################################↵
    0.06
     случа
    0.06
    ék
    0.06
     APPRO
    0.06
     Example
    0.06
     лок
    0.06
     голови
    0.06
     zám
    0.06
    ольз
    0.06
    Act Density 0.068%

    No Known Activations