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

    Neuronpedia

    INDEX
    Explanations

    (M

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     disguised
    -0.06
    .Language
    -0.06
    InlineData
    -0.06
    PRESENT
    -0.06
    RequestMethod
    -0.06
    pone
    -0.06
    \uD
    -0.06
     nave
    -0.06
    typescript
    -0.06
    TreeWidgetItem
    -0.06
    POSITIVE LOGITS
     revoke
    0.08
     Attribution
    0.07
     website
    0.06
     New
    0.06
     zarar
    0.06
    ivial
    0.06
     TO
    0.06
     Essential
    0.06
    (nodes
    0.06
     essential
    0.06
    Act Density 0.000%

    No Known Activations