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

    Neuronpedia

    INDEX
    Explanations

    typing or writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Vector
    -0.07
    _outputs
    -0.07
    parameters
    -0.07
    moved
    -0.06
    ：“
    -0.06
     rushes
    -0.06
     attenu
    -0.06
    arius
    -0.06
     mango
    -0.06
     maintained
    -0.06
    POSITIVE LOGITS
    .Iter
    0.07
    Issue
    0.06
     disaster
    0.06
    expire
    0.06
     Deleted
    0.06
    Expected
    0.06
     ….
    0.06
     celé
    0.06
     wrinkles
    0.06
    ục
    0.06
    Act Density 0.017%

    No Known Activations