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

    Neuronpedia

    INDEX
    Explanations

    directions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (mode
    -0.07
    .toCharArray
    -0.06
    절차
    -0.06
     uns
    -0.06
     Academic
    -0.06
     Bootstrap
    -0.06
    angs
    -0.06
    ünchen
    -0.06
    /index
    -0.06
     periodic
    -0.06
    POSITIVE LOGITS
    功用
    0.08
    /client
    0.08
     Clim
    0.07
     filmed
    0.07
    薄膜
    0.07
    防御
    0.07
    Information
    0.07
     dine
    0.07
     �
    0.07
    bundles
    0.07
    Act Density 0.002%

    No Known Activations