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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Lesbian
    -0.07
     našeho
    -0.07
    ड
    -0.07
    laması
    -0.07
     delicate
    -0.06
     executing
    -0.06
     culpa
    -0.06
     lively
    -0.06
     Mold
    -0.06
    -btn
    -0.06
    POSITIVE LOGITS
     }}">
    0.07
     現
    0.07
    (SQLException
    0.07
    >(↵
    0.06
     تط
    0.06
     murky
    0.06
    mayı
    0.06
    》（
    0.06
     ”↵↵
    0.06
    __.'/
    0.06
    Act Density 0.066%

    No Known Activations