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

    Neuronpedia

    INDEX
    Explanations

    Security/permissions context

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     rng
    -0.07
     matchups
    -0.07
     talk
    -0.06
     entrepreneur
    -0.06
     Babies
    -0.06
     apocalypse
    -0.06
     thirsty
    -0.06
    -header
    -0.06
    937
    -0.06
    shift
    -0.06
    POSITIVE LOGITS
    alıdır
    0.07
     ue
    0.07
    авлива
    0.06
    зація
    0.06
     ALIGN
    0.06
     Listed
    0.06
     CONSTANT
    0.06
    IMPLEMENT
    0.06
     Nationwide
    0.06
    oenix
    0.06
    Act Density 0.172%

    No Known Activations