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

    Neuronpedia

    INDEX
    Explanations

    rates

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    indows
    -0.06
    }-{
    -0.06
    OLF
    -0.06
     ():
    -0.06
    ynomial
    -0.06
     headed
    -0.06
     상대
    -0.06
    ukan
    -0.06
     Receive
    -0.06
    (Position
    -0.06
    POSITIVE LOGITS
     marca
    0.06
     ener
    0.06
    increase
    0.06
    	scope
    0.06
     독
    0.06
    different
    0.06
    らず
    0.06
     warrant
    0.06
    Southern
    0.06
    ]')↵
    0.06
    Act Density 0.006%

    No Known Activations