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

    Neuronpedia

    INDEX
    Explanations

    AssemblyDescription

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    woocommerce
    -0.07
    ício
    -0.07
    _choice
    -0.07
    	esc
    -0.06
    尽
    -0.06
     mystery
    -0.06
     Bl
    -0.06
    奂
    -0.06
    Ὃ
    -0.06
     Sociology
    -0.06
    POSITIVE LOGITS
    (crate
    0.07
    ERRY
    0.07
    {_
    0.07
    蒡
    0.07
    ᕗ
    0.07
    (opts
    0.07
    病房
    0.07
    YOUR
    0.07
     Bard
    0.07
    {↵
    0.07
    Act Density 0.000%

    No Known Activations