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

    Neuronpedia

    INDEX
    Explanations

    USSR

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Nine
    -0.09
    אופן
    -0.08
    经理
    -0.07
     courses
    -0.07
     instanceof
    -0.07
     arrives
    -0.07
    情形
    -0.07
     rise
    -0.07
    ☏
    -0.07
    政策措施
    -0.07
    POSITIVE LOGITS
    .getAbsolutePath
    0.08
    */
↵
    0.07
     cream
    0.07
    flammatory
    0.07
     ****
    0.07
     paul
    0.07
    -block
    0.06
    ربح
    0.06
    ulary
    0.06
    �
    0.06
    Act Density 0.005%

    No Known Activations