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

    Neuronpedia

    INDEX
    Explanations

    helpful

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    破解
    -0.08
    ート
    -0.07
    �述
    -0.07
    .action
    -0.07
     tor
    -0.07
    �回
    -0.07
    -ton
    -0.07
    etically
    -0.06
    :-
    -0.06
    궜
    -0.06
    POSITIVE LOGITS
    (fname
    0.07
    (lst
    0.07
     "::
    0.07
     fk
    0.07
    вшис
    0.07
    verage
    0.07
     viewWillAppear
    0.07
     Fernandez
    0.07
     $('#'
    0.07
    津贴
    0.06
    Act Density 0.001%

    No Known Activations