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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _snd
    -0.07
     legality
    -0.07
    �
    -0.07
    sons
    -0.06
    луг
    -0.06
     KN
    -0.06
    idy
    -0.06
    厚
    -0.06
    =log
    -0.06
     день
    -0.06
    POSITIVE LOGITS
    -'+
    0.07
     novelist
    0.07
    lovak
    0.06
    АР
    0.06
     Rou
    0.06
    plane
    0.06
     ):↵↵
    0.06
    -system
    0.06
     edilen
    0.06
    	mat
    0.06
    Act Density 0.033%

    No Known Activations