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

    Neuronpedia

    INDEX
    Explanations

    Negation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    !/
    -0.06
     пас
    -0.06
    _CA
    -0.06
     Commerce
    -0.06
    دن
    -0.06
     Amph
    -0.06
     Indicator
    -0.06
     Sinh
    -0.06
     Working
    -0.06
     Fuck
    -0.05
    POSITIVE LOGITS
    ดำ
    0.07
     Formation
    0.07
     footwear
    0.06
     قابل
    0.06
    �
    0.06
     نويس
    0.06
    ITEM
    0.06
     процесса
    0.06
     uma
    0.06
     nicotine
    0.06
    Act Density 0.035%

    No Known Activations