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

    Neuronpedia

    INDEX
    Explanations

    period

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ーラ
    -0.07
     Ferd
    -0.07
    ont
    -0.07
    िसक
    -0.06
    ipel
    -0.06
    ット
    -0.06
    _dll
    -0.06
    quez
    -0.06
     territorial
    -0.06
    plorer
    -0.06
    POSITIVE LOGITS
    	mutex
    0.07
    .foundation
    0.07
     progression
    0.06
    }}↵↵
    0.06
    \',
    0.06
    >',↵
    0.06
    (input
    0.06
     默认
    0.06
     enumeration
    0.06
    #else
    0.06
    Act Density 0.001%

    No Known Activations