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

    Neuronpedia

    INDEX
    Explanations

    uses the letter 't' to demonstrate simple mathematical concepts

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    pec
    -0.06
    reur
    -0.06
     needles
    -0.06
    apan
    -0.06
    -urlencoded
    -0.06
    Ñľ
    -0.06
    eniz
    -0.06
    ä¸įè¦ģ
    -0.06
     sqrt
    -0.06
     Gregg
    -0.06
    POSITIVE LOGITS
    èĩ³å°ij
    0.14
     minimum
    0.14
     Minimum
    0.12
    Minimum
    0.12
     âī¥
    0.12
    minimum
    0.12
     atleast
    0.11
     least
    0.10
     smallest
    0.10
     >=
    0.10
    Act Density 0.250%

    No Known Activations