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

    Neuronpedia

    INDEX
    Explanations

    B

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Boulder
    -0.07
    ีฟ
    -0.06
    	headers
    -0.06
     Jaguars
    -0.06
     센
    -0.06
    .tx
    -0.06
     jade
    -0.06
    تامبر
    -0.06
    _TOPIC
    -0.06
    billing
    -0.06
    POSITIVE LOGITS
     achie
    0.06
     dovol
    0.06
    (CONFIG
    0.06
     zakáz
    0.06
    .addElement
    0.06
     كام
    0.06
    OURCES
    0.06
     pci
    0.06
    cpy
    0.06
    ?>↵↵
    0.06
    Act Density 0.012%

    No Known Activations