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

    Neuronpedia

    INDEX
    Explanations

    pronouns

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     giảng
    -0.07
     Stanford
    -0.07
    .Fixed
    -0.07
    átu
    -0.07
     Ember
    -0.07
    κτή
    -0.07
     mortality
    -0.07
    ocode
    -0.07
    ании
    -0.06
     capitalist
    -0.06
    POSITIVE LOGITS
    ueil
    0.07
     textbox
    0.06
    	account
    0.06
    .mob
    0.06
    pects
    0.06
    ม
    0.06
    Bed
    0.06
     $('<
    0.06
    .removeClass
    0.06
    :]↵↵
    0.06
    Act Density 0.130%

    No Known Activations