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

    Neuronpedia

    INDEX
    Explanations

    contain

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Pro
    -0.07
     pretty
    -0.07
     bump
    -0.07
     increasingly
    -0.07
     �
    -0.07
    僕
    -0.06
    이슈
    -0.06
    选
    -0.06
     bumps
    -0.06
     zoo
    -0.06
    POSITIVE LOGITS
     contain
    0.12
     contains
    0.11
     containing
    0.10
     contained
    0.10
     Contains
    0.10
    َن
    0.07
     Holds
    0.07
     >",
    0.07
    sealed
    0.07
    aman
    0.07
    Act Density 0.041%

    No Known Activations