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

    Neuronpedia

    INDEX
    Explanations

    say "the"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    			↵
    -0.06
     minds
    -0.06
    Themes
    -0.06
     paradise
    -0.06
     五
    -0.06
     major
    -0.06
     Quarter
    -0.06
     substantial
    -0.06
    /th
    -0.06
    .Add
    -0.06
    POSITIVE LOGITS
    }-{
    0.07
    ́t
    0.07
     आए
    0.07
     Pars
    0.07
    -Ray
    0.06
    stown
    0.06
    urray
    0.06
    _operations
    0.06
     Fleet
    0.06
    Nhap
    0.06
    Act Density 0.186%

    No Known Activations