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

    Neuronpedia

    INDEX
    Explanations

    pre

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    natal
    -0.07
     tàu
    -0.07
     noci
    -0.07
     seeded
    -0.06
     पद
    -0.06
    onis
    -0.06
     retreated
    -0.06
    amine
    -0.06
    との
    -0.06
    azers
    -0.06
    POSITIVE LOGITS
     pre
    0.08
    SAM
    0.07
     Mu
    0.07
     commence
    0.06
     spokeswoman
    0.06
    Wy
    0.06
     Beginner
    0.06
     iam
    0.06
     remake
    0.06
     Beast
    0.06
    Act Density 0.009%

    No Known Activations