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

    Neuronpedia

    INDEX
    Explanations

    baking instructions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .am
    -0.08
    종
    -0.07
    fair
    -0.07
    Font
    -0.07
    _Font
    -0.07
     Lands
    -0.06
    <?=$
    -0.06
    .ot
    -0.06
    \d
    -0.06
    \User
    -0.06
    POSITIVE LOGITS
     certif
    0.07
    žití
    0.06
     Aut
    0.06
     Discover
    0.06
    masından
    0.06
     Sidney
    0.06
    masına
    0.06
     Accepted
    0.06
    骨
    0.06
    成為
    0.06
    Act Density 0.027%

    No Known Activations