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

    Neuronpedia

    INDEX
    Explanations

    Data backups

    np_max-act · gemini-2.0-flash

    The neuron detects mentions of “backup” (and its variants like “backups,” “back up,” etc.) in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     frequencies
    -0.08
     demon
    -0.07
     strips
    -0.07
    रण
    -0.06
    _until
    -0.06
    査
    -0.06
    549
    -0.06
     spherical
    -0.06
    weight
    -0.06
     Moore
    -0.06
    POSITIVE LOGITS
     Prosec
    0.06
     Pharmac
    0.06
    etxt
    0.06
    icultural
    0.06
    _TER
    0.06
    userInfo
    0.06
     texting
    0.06
    verture
    0.06
    .fields
    0.06
     최근
    0.06
    Act Density 0.024%

    No Known Activations