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

    Neuronpedia

    INDEX
    Explanations

    not

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    联盟
    -0.06
     ROC
    -0.06
     né
    -0.06
     Nobody
    -0.06
     Russo
    -0.06
    Sibling
    -0.06
    ，又
    -0.06
    _bet
    -0.06
    Document
    -0.06
    нок
    -0.06
    POSITIVE LOGITS
     milieu
    0.07
    来源
    0.07
     }}>↵
    0.06
    expression
    0.06
    .AppendText
    0.06
    	background
    0.06
     Villa
    0.06
    _opts
    0.06
    .activation
    0.06
     Condition
    0.06
    Act Density 0.000%

    No Known Activations