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

    Neuronpedia

    INDEX
    Explanations

    Written text

    np_max-act · gemini-2.0-flash

    This neuron detects mentions of postpartum health conditions (e.g., “infection,” “blues,” “psychosis”) in a list.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    Availability
    -0.06
    To
    -0.06
     Biom
    -0.06
     parallel
    -0.06
    legalArgumentException
    -0.06
     Feed
    -0.06
     Morph
    -0.06
    !/
    -0.06
    (Float
    -0.06
    hol
    -0.06
    POSITIVE LOGITS
     муж
    0.07
     لأ
    0.06
     Cust
    0.06
     nog
    0.06
    -quality
    0.06
     الب
    0.06
     Procedure
    0.06
     ΕΛ
    0.06
     Dropbox
    0.06
    issional
    0.06
    Act Density 0.027%

    No Known Activations