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

    Neuronpedia

    INDEX
    Explanations

    age

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    老实
    -0.07
    failed
    -0.07
    illos
    -0.07
    更好
    -0.07
    到底
    -0.07
    习近平
    -0.07
     Sob
    -0.06
     akin
    -0.06
     Pitt
    -0.06
     وجه
    -0.06
    POSITIVE LOGITS
     HS
    0.08
    Processes
    0.08
     //////////////////////////////////////////////////////////////////////
    0.07
    unci
    0.07
     Events
    0.07
     Bulgarian
    0.07
     Frame
    0.07
    (option
    0.07
    Daemon
    0.07
    ทร
    0.07
    Act Density 0.002%

    No Known Activations