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

    Neuronpedia

    INDEX
    Explanations

    examples of mathematical problems being solved, especially how numbers fit equations

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Encoded
    -0.06
    oder
    -0.06
     Pik
    -0.06
    éłħ
    -0.06
    armed
    -0.06
    icans
    -0.06
     Cyrus
    -0.06
    arming
    -0.06
     chances
    -0.06
    ucs
    -0.06
    POSITIVE LOGITS
     example
    0.10
    ä¾ĭ
    0.09
    example
    0.08
    -example
    0.07
    $MESS
    0.07
    å·±
    0.07
    ênh
    0.07
     examples
    0.07
    Example
    0.07
    .example
    0.07
    Act Density 1.453%

    No Known Activations