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

    Neuronpedia

    INDEX
    Explanations

    android

    np_max-act · gemini-2.0-flash

    This neuron identifies decimal numeric tokens (floating‐point numbers) in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     NSDate
    -0.07
    Portal
    -0.06
     Advisors
    -0.06
     Rai
    -0.06
    맥
    -0.06
     Dataset
    -0.06
     counselors
    -0.06
     reviews
    -0.06
    곤
    -0.06
     разви
    -0.06
    POSITIVE LOGITS
    ΗΜ
    0.07
    _sum
    0.07
    _upgrade
    0.07
     �
    0.06
    median
    0.06
    _modal
    0.06
    ，与
    0.06
    extra
    0.06
    やす
    0.06
    .success
    0.06
    Act Density 0.005%

    No Known Activations