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

    Neuronpedia

    INDEX
    Explanations

    Back

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    todos
    -0.07
     แต
    -0.06
    (issue
    -0.06
    rální
    -0.06
     dots
    -0.06
    -tools
    -0.06
    )){
↵
    -0.06
    ро
    -0.06
    лами
    -0.06
     breve
    -0.06
    POSITIVE LOGITS
    deniz
    0.07
    icí
    0.06
    egis
    0.06
     discreet
    0.06
     Desert
    0.06
     Jain
    0.06
    @register
    0.06
    reek
    0.06
    %H
    0.06
    天天
    0.06
    Act Density 0.010%

    No Known Activations