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

    Neuronpedia

    INDEX
    Explanations

    complex math and reasoning

    oai_token-act-pair · gemini-2.0-flash

    mathematical expressions and equations containing variables and numerical operations.

    oai_token-act-pair · claude-4-5-haikuTriggered by @hermannandreas
    New Auto-Interp
    Negative Logits
    дина
    -0.07
    umont
    -0.07
    oad
    -0.06
     putas
    -0.06
    átor
    -0.06
    aseline
    -0.06
    ozem
    -0.06
    ียà¸ļ
    -0.06
    rides
    -0.06
    Inlining
    -0.06
    POSITIVE LOGITS
    0.07
    ans
    0.06
     Later
    0.06
    chten
    0.06
     III
    0.06
     DISCLAIM
    0.06
    ambi
    0.06
     unrelated
    0.06
     latter
    0.06
    _vlog
    0.06
    Act Density 0.112%

    No Known Activations