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

    Neuronpedia

    INDEX
    Explanations

    nore

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     aaa
    -0.08
    _URL
    -0.07
     sewing
    -0.07
     im
    -0.06
    _elt
    -0.06
    十三
    -0.06
    우스
    -0.06
    (loss
    -0.06
     Друг
    -0.06
    gist
    -0.06
    POSITIVE LOGITS
    nore
    0.08
     tainted
    0.07
    angled
    0.06
    customer
    0.06
    "|
    0.06
     Throw
    0.06
    _customer
    0.06
    Workers
    0.06
    breaking
    0.06
    Cause
    0.06
    Act Density 0.000%

    No Known Activations