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

    Neuronpedia

    INDEX
    Explanations

    tox

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Bac
    -0.07
     Respons
    -0.07
    )."
    -0.07
     Mal
    -0.07
     pav
    -0.07
    ⛾
    -0.07
     product
    -0.06
    occasion
    -0.06
    ."
    -0.06
     robes
    -0.06
    POSITIVE LOGITS
    月下
    0.07
    型
    0.07
    声明
    0.07
     CGPointMake
    0.07
    uled
    0.07
    LOT
    0.07
    なぜ
    0.07
    代码
    0.07
    白癜
    0.06
    	echo
    0.06
    Act Density 0.003%

    No Known Activations