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

    Neuronpedia

    INDEX
    Explanations

    tragedies and flaws

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ﳤ
    -0.07
     option
    -0.07
    Calling
    -0.07
    )|
    -0.06
     English
    -0.06
     infinit
    -0.06
     MX
    -0.06
    创意
    -0.06
     transformation
    -0.06
    槃
    -0.06
    POSITIVE LOGITS
    篌
    0.07
    Couldn
    0.07
    					↵
    0.07
     Patri
    0.07
    ске
    0.07
    руг
    0.07
    Ник
    0.07
     Wäh
    0.06
     новых
    0.06
    estic
    0.06
    Act Density 0.010%

    No Known Activations