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

    Neuronpedia

    INDEX
    Explanations

    numerical computations or mathematical expressions

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ursal
    -0.07
    tron
    -0.06
    Preview
    -0.06
     caps
    -0.06
     Newsletter
    -0.06
    pon
    -0.06
     helf
    -0.06
    errer
    -0.06
    æľŁ
    -0.06
    olec
    -0.06
    POSITIVE LOGITS
     precise
    0.11
     exact
    0.11
     precisely
    0.09
    ç²¾
    0.09
     exactly
    0.09
     Exact
    0.08
     accurate
    0.08
     precision
    0.08
    Round
    0.08
     accurately
    0.08
    Act Density 0.193%

    No Known Activations