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

    Neuronpedia

    INDEX
    Explanations

    forum posts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	list
    -0.07
    ़न
    -0.07
    받
    -0.07
    	cd
    -0.06
    sports
    -0.06
    ulması
    -0.06
    ких
    -0.06
    ReturnType
    -0.06
    reb
    -0.06
     lists
    -0.06
    POSITIVE LOGITS
    .Package
    0.07
    _hpp
    0.06
     Tune
    0.06
     giao
    0.06
     Escorts
    0.06
     údajů
    0.06
    につ
    0.06
    toMatchSnapshot
    0.06
     });
↵
    0.06
     "__
    0.06
    Act Density 0.020%

    No Known Activations