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

    Neuronpedia

    INDEX
    Explanations

    x

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (indices
    -0.07
    𝙪
    -0.07
    我认为
    -0.07
    舒心
    -0.07
    Ū
    -0.07
    inel
    -0.07
     �
    -0.06
    	Action
    -0.06
    ᐃ
    -0.06
    cbd
    -0.06
    POSITIVE LOGITS
    }.${
    0.08
    ":"+
    0.07
    ouncer
    0.07
     OSP
    0.07
    	AND
    0.07
     صفحة
    0.07
     photographers
    0.07
    жа
    0.07
     Mountain
    0.07
     SN
    0.07
    Act Density 0.000%

    No Known Activations