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

    Neuronpedia

    INDEX
    Explanations

    Code and web snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .image
    -0.07
    ingle
    -0.07
    _Item
    -0.07
     weaken
    -0.06
     vene
    -0.06
     Trying
    -0.06
     finger
    -0.06
     guild
    -0.06
    การต
    -0.06
     bri
    -0.06
    POSITIVE LOGITS
    =G
    0.07
    олог
    0.07
    ترنت
    0.07
    (UnmanagedType
    0.06
    Currently
    0.06
    0.06
    боратор
    0.06
    _dependencies
    0.06
    科技有限公司
    0.06
    (ws
    0.06
    Act Density 0.011%

    No Known Activations