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

    Neuronpedia

    INDEX
    Explanations

    writing techniques

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     carte
    -0.07
     called
    -0.07
    AS
    -0.07
    .StringVar
    -0.07
    (predicate
    -0.07
    ("{
    -0.07
     "@"
    -0.06
    =E
    -0.06
     below
    -0.06
     Jelly
    -0.06
    POSITIVE LOGITS
    uj
    0.06
     kj
    0.06
    (groups
    0.06
    _episode
    0.06
     폐
    0.06
     mess
    0.06
    estation
    0.06
    cab
    0.06
    -&
    0.06
     퍼
    0.06
    Act Density 0.034%

    No Known Activations