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

    Neuronpedia

    INDEX
    Explanations

    processes and changes

    np_max-act · gemini-2.0-flash

    This neuron activates on numeric tokens representing floating‐point numbers (decimal numbers).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     you
    -0.06
     withd
    -0.06
    >You
    -0.06
     threats
    -0.06
     Bobby
    -0.06
    [h
    -0.06
    immune
    -0.06
    равиль
    -0.06
     Brief
    -0.06
    TD
    -0.06
    POSITIVE LOGITS
    ---------↵↵
    0.08
    ])-
    0.07
    anding
    0.07
     restarting
    0.07
     MPG
    0.07
     μικ
    0.07
     násled
    0.07
     township
    0.06
    ंस
    0.06
     temperament
    0.06
    Act Density 0.223%

    No Known Activations