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

    Neuronpedia

    INDEX
    Explanations

    $

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     WITH
    -0.07
    _OF
    -0.07
     rusty
    -0.06
    Like
    -0.06
    _products
    -0.06
     Lau
    -0.06
    ิ้
    -0.06
     LTE
    -0.06
    .seq
    -0.06
     flashes
    -0.06
    POSITIVE LOGITS
     "$
    0.16
     `$
    0.12
    ("$
    0.11
     ['$
    0.09
    "$
    0.08
     "${
    0.08
    ["$
    0.07
    ','$
    0.07
    ="$(
    0.07
    uju
    0.07
    Act Density 0.004%

    No Known Activations