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

    Neuronpedia

    INDEX
    Explanations

    Connecting words in titles

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    }},
    -0.06
    чів
    -0.06
    limited
    -0.06
     Shir
    -0.06
    Linked
    -0.06
     implies
    -0.06
     نوشته
    -0.06
    _UART
    -0.06
    -css
    -0.06
    -p
    -0.06
    POSITIVE LOGITS
    retrieve
    0.08
     rr
    0.06
    πως
    0.06
    ্
    0.06
     Pods
    0.06
    (Db
    0.06
    unched
    0.06
    _minor
    0.06
     बय
    0.06
     electrode
    0.06
    Act Density 0.088%

    No Known Activations