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

    Neuronpedia

    INDEX
    Explanations

    migration

    np_max-act · gemini-2.0-flash

    The neuron is picking up on numeric and measurement terms (e.g. distances, frequencies, units, and related quantifiers).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    Money
    -0.07
     Updates
    -0.06
    Π
    -0.06
     بح
    -0.06
    tolua
    -0.06
     Frederick
    -0.06
    ером
    -0.06
    ために
    -0.06
     Blob
    -0.06
    du
    -0.06
    POSITIVE LOGITS
    FilterWhere
    0.06
    _working
    0.06
    -xs
    0.06
     مسجد
    0.06
     천
    0.06
    rocessing
    0.06
    .nn
    0.06
    สะดวก
    0.06
    .grad
    0.06
    を見る
    0.06
    Act Density 0.012%

    No Known Activations