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

    Neuronpedia

    INDEX
    Explanations

    hello

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     cultivated
    -0.07
     дані
    -0.07
     gangs
    -0.06
     roc
    -0.06
    따
    -0.06
    )은
    -0.06
    \Middleware
    -0.06
    scratch
    -0.06
     Retirement
    -0.06
     rele
    -0.06
    POSITIVE LOGITS
    هایی
    0.07
    elta
    0.06
    nk
    0.06
     플레이
    0.06
    ns
    0.06
     рух
    0.06
     Coordinator
    0.06
     somehow
    0.06
    Atom
    0.06
    	Item
    0.06
    Act Density 0.015%

    No Known Activations