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

    Neuronpedia

    INDEX
    Explanations

    visual depth and dimension

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    alis
    -0.07
     part
    -0.07
    =t
    -0.07
     font
    -0.07
    sar
    -0.07
     bst
    -0.07
     andre
    -0.07
     Accent
    -0.07
    防火
    -0.07
    far
    -0.07
    POSITIVE LOGITS
     �
    0.08
    甚么
    0.07
    lobber
    0.06
    导向
    0.06
    מדובר
    0.06
     משתמש
    0.06
    續
    0.06
    �
    0.06
    鏖
    0.06
     נשמע
    0.06
    Act Density 0.022%

    No Known Activations