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

    Neuronpedia

    INDEX
    Explanations

    prevention

    np_max-act · gemini-2.0-flash

    the neuron detects present‐tense verbs or gerunds ending in “-ing.”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     бла
    -0.08
    _DATABASE
    -0.07
    _mag
    -0.07
    .SaveChanges
    -0.07
    AV
    -0.06
    ng
    -0.06
     getItem
    -0.06
    呼
    -0.06
     берез
    -0.06
    _wire
    -0.06
    POSITIVE LOGITS
    rance
    0.06
     IDS
    0.06
    SuccessListener
    0.06
    ataires
    0.06
    Ins
    0.06
     smelled
    0.06
    gam
    0.06
    photos
    0.06
     polled
    0.06
    wers
    0.06
    Act Density 0.051%

    No Known Activations