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

    Neuronpedia

    INDEX
    Explanations

    drinking

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    icens
    -0.07
    engers
    -0.07
    Base
    -0.07
    (Bundle
    -0.07
    )))
    -0.07
    <QString
    -0.07
    这是因为
    -0.07
     reason
    -0.07
    icester
    -0.06
     Burr
    -0.06
    POSITIVE LOGITS
    常态化
    0.07
    азв
    0.07
    Attrib
    0.06
    住宿
    0.06
    中小学
    0.06
    	rec
    0.06
    forced
    0.06
    _PF
    0.06
    多样化
    0.06
    能否
    0.06
    Act Density 0.003%

    No Known Activations