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

    Neuronpedia

    INDEX
    Explanations

    Not harmful

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ecstasy
    -0.07
    Favorites
    -0.06
    ucken
    -0.06
     aprove
    -0.06
     هایی
    -0.06
    cılar
    -0.06
     mạnh
    -0.06
    ="../../
    -0.06
     ************************************************
    -0.06
    と思う
    -0.06
    POSITIVE LOGITS
     harmless
    0.08
     manifestations
    0.07
    вают
    0.07
    idual
    0.07
    owment
    0.07
    few
    0.07
     strand
    0.07
     leased
    0.06
     Ahmad
    0.06
     scenery
    0.06
    Act Density 0.002%

    No Known Activations