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

    Neuronpedia

    INDEX
    Explanations

    unusual words

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     crops
    -0.06
    allows
    -0.06
    aldi
    -0.06
    _ptrs
    -0.06
    cri
    -0.06
     Jeho
    -0.06
    ordes
    -0.06
    svm
    -0.06
     Forest
    -0.05
    кти
    -0.05
    POSITIVE LOGITS
    };↵↵
    0.07
     varias
    0.07
     almost
    0.07
     acquaintance
    0.07
    	Ext
    0.07
    Архів
    0.07
    .dsl
    0.07
     ↵    ↵
    0.06
     FB
    0.06
     (*
    0.06
    Act Density 0.065%

    No Known Activations