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

    Neuronpedia

    INDEX
    Explanations

    orum

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     alguns
    -0.07
     اند
    -0.06
    rename
    -0.06
    ată
    -0.06
    "),"
    -0.06
     entreg
    -0.06
    asyon
    -0.06
    令人
    -0.06
     пев
    -0.06
     unanimously
    -0.06
    POSITIVE LOGITS
     Flynn
    0.08
    うん
    0.07
     органів
    0.07
     Gar
    0.06
     Manufacturing
    0.06
    請
    0.06
     Moral
    0.06
     crave
    0.06
    .signature
    0.06
     Rolling
    0.06
    Act Density 0.001%

    No Known Activations