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

    Neuronpedia

    INDEX
    Explanations

    withdrawal

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    쮜
    -0.08
    venture
    -0.07
     AZ
    -0.07
     Gaz
    -0.07
     leading
    -0.07
    菅
    -0.07
     genetic
    -0.07
    烙
    -0.07
    Ϝ
    -0.07
    胂
    -0.07
    POSITIVE LOGITS
    を変え
    0.07
     ("-
    0.07
     وبالتالي
    0.07
    _entities
    0.07
     prostitute
    0.07
    香菇
    0.07
    损害
    0.07
    工程技术
    0.07
    תקשר
    0.06
     disorders
    0.06
    Act Density 0.004%

    No Known Activations