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

    Neuronpedia

    INDEX
    Explanations

    Programming code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     至
    -0.07
     goes
    -0.07
    .amazonaws
    -0.06
    _actions
    -0.06
    495
    -0.06
    嫌
    -0.06
    VELO
    -0.06
     '%'
    -0.06
    их
    -0.06
    -has
    -0.06
    POSITIVE LOGITS
     břez
    0.06
     Listing
    0.06
    asing
    0.06
     referenced
    0.06
     Naples
    0.06
    /el
    0.06
     referencing
    0.06
     кис
    0.06
    Producto
    0.06
    segment
    0.06
    Act Density 0.053%

    No Known Activations