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

    Neuronpedia

    INDEX
    Explanations

    colons

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _rad
    -0.07
    营业执照
    -0.07
     curled
    -0.07
    	Id
    -0.07
     Cuando
    -0.07
    	If
    -0.07
    esis
    -0.07
    كلف
    -0.07
     flourish
    -0.06
     Süd
    -0.06
    POSITIVE LOGITS
     '~
    0.07
    检测
    0.07
    AJOR
    0.07
    ⼈
    0.07
    ====
    0.06
     Cameras
    0.06
    घ
    0.06
     heavier
    0.06
    �
    0.06
     Foster
    0.06
    Act Density 0.111%

    No Known Activations