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

    Neuronpedia

    INDEX
    Explanations

    period

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Rita
    -0.08
    006
    -0.07
     passe
    -0.07
    HU
    -0.07
     seinem
    -0.07
    ducers
    -0.07
     fait
    -0.07
    納
    -0.06
    ्यत
    -0.06
    kea
    -0.06
    POSITIVE LOGITS
    -terrorism
    0.06
     propel
    0.06
     DropIndex
    0.06
    Registry
    0.06
    ден
    0.06
    velop
    0.06
     νεφοκάλυψης
    0.06
     Profile
    0.06
    prisingly
    0.06
     pedigree
    0.06
    Act Density 0.000%

    No Known Activations