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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     psychologist
    -0.07
    _file
    -0.07
    ltra
    -0.07
    ุนายน
    -0.07
    Headers
    -0.07
    Houston
    -0.07
    ήλ
    -0.07
    Record
    -0.07
     recording
    -0.06
    .mysql
    -0.06
    POSITIVE LOGITS
     kesinlikle
    0.07
     G
    0.06
    原
    0.06
     بگ
    0.06
    plet
    0.06
     descargar
    0.06
    創
    0.06
    	P
    0.06
    인이
    0.06
     Söz
    0.05
    Act Density 0.005%

    No Known Activations