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

    Neuronpedia

    INDEX
    Explanations

    Initials

    np_max-act · gemini-2.0-flash

    This neuron spotlights reference‐style author initials (single capital letters followed by a period) in bibliographic citations.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    riors
    -0.07
    ูม
    -0.06
     معمول
    -0.06
    ức
    -0.06
    .ToArray
    -0.06
    Invocation
    -0.06
     snap
    -0.06
    روم
    -0.06
     cans
    -0.06
     insurer
    -0.06
    POSITIVE LOGITS
    -h
    0.07
    ATHER
    0.06
    uding
    0.06
    <Tuple
    0.06
    HEY
    0.06
    istant
    0.06
     حفظ
    0.06
     гал
    0.06
    AAA
    0.06
    udes
    0.06
    Act Density 0.011%

    No Known Activations