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

    Neuronpedia

    INDEX
    Explanations

    with

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	↵	↵	↵	↵
    -0.07
     İb
    -0.07
     erotische
    -0.06
     cnn
    -0.06
    ैं।↵↵
    -0.06
     浙江
    -0.06
     кноп
    -0.06
    addAll
    -0.06
     };
↵
↵
    -0.06
    sWith
    -0.06
    POSITIVE LOGITS
     filters
    0.07
    Kir
    0.07
     filter
    0.06
    kg
    0.06
    .phi
    0.06
     jurors
    0.06
     unary
    0.06
     filtro
    0.06
    ília
    0.06
    uber
    0.06
    Act Density 0.000%

    No Known Activations