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

    Neuronpedia

    INDEX
    Explanations

    officials

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     []),↵
    -0.07
    best
    -0.07
     openid
    -0.07
     HUGE
    -0.06
     doit
    -0.06
     presum
    -0.06
    	Request
    -0.06
    Crop
    -0.06
    .market
    -0.06
     dumb
    -0.06
    POSITIVE LOGITS
    SER
    0.07
     combinations
    0.07
    Argument
    0.06
    idi
    0.06
     sınav
    0.06
     논
    0.06
    liquid
    0.06
    責
    0.06
    sono
    0.06
     Stevenson
    0.06
    Act Density 0.017%

    No Known Activations