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

    Neuronpedia

    INDEX
    Explanations

    by

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     나라
    -0.06
     Draco
    -0.06
    Turkey
    -0.06
     комплек
    -0.06
     induction
    -0.06
     etwas
    -0.06
     denomin
    -0.06
     loosen
    -0.06
    nob
    -0.06
     às
    -0.06
    POSITIVE LOGITS
     tether
    0.07
    SHIFT
    0.07
    _segments
    0.06
    طي
    0.06
     ArrayCollection
    0.06
     complaints
    0.06
    cle
    0.06
     premiere
    0.06
    .Microsoft
    0.06
     Λ
    0.06
    Act Density 0.001%

    No Known Activations