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

    Neuronpedia

    INDEX
    Explanations

    points

    np_max-act · gemini-2.0-flash

    This neuron fires on fractional numeric tokens (decimal parts of numbers).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     estimation
    -0.07
    BackColor
    -0.06
    DOMAIN
    -0.06
     वस
    -0.06
     approximation
    -0.06
     Population
    -0.06
     claims
    -0.06
    Rel
    -0.06
    AUSE
    -0.06
     system
    -0.06
    POSITIVE LOGITS
    ("^
    0.07
    ://'
    0.07
     Southeast
    0.07
    \"]
    0.07
    新的
    0.07
     tweeting
    0.07
    clair
    0.07
    елов
    0.06
    .Here
    0.06
     '');↵
    0.06
    Act Density 0.007%

    No Known Activations