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

    Neuronpedia

    INDEX
    Explanations

    questions about problems

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    tbl
    -0.07
    TRACE
    -0.07
    ]){↵
    -0.06
     Dans
    -0.06
    /time
    -0.06
    kp
    -0.06
    esity
    -0.06
    mk
    -0.06
    nan
    -0.06
     neby
    -0.06
    POSITIVE LOGITS
    nowled
    0.07
     equilibrium
    0.06
    Window
    0.06
     như
    0.06
     likely
    0.06
     Axel
    0.06
     Κ
    0.06
    領
    0.06
    	buff
    0.06
     Qt
    0.06
    Act Density 0.001%

    No Known Activations