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

    Neuronpedia

    INDEX
    Explanations

    �

    np_max-act · gemini-2.0-flash

    This neuron fires on non-ASCII or unusual Unicode tokens (e.g. CJK characters or garbled byte sequences).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Chick
    -0.08
    .urlencoded
    -0.07
    inging
    -0.07
    BAT
    -0.07
    _gain
    -0.07
    Insurance
    -0.07
    ={}↵
    -0.07
    Bal
    -0.07
    Sharp
    -0.07
    Donald
    -0.07
    POSITIVE LOGITS
    �
    0.10
    DEFINE
    0.06
     Vest
    0.06
     tuyên
    0.06
     INTERN
    0.06
     MPS
    0.06
     견
    0.06
     svens
    0.06
    思
    0.06
     Tone
    0.06
    Act Density 0.001%

    No Known Activations