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

    Neuronpedia

    INDEX
    Explanations

    1

    np_max-act · gemini-2.0-flash

    This neuron detects sequences of numeric expressions and arithmetic operations (e.g. fractions, sums, products, orderings).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ้ำ
    -0.08
     Pv
    -0.07
     göç
    -0.07
    -ph
    -0.06
     Policy
    -0.06
    .ts
    -0.06
    sec
    -0.06
    urtles
    -0.06
     fanatic
    -0.06
     nám
    -0.06
    POSITIVE LOGITS
    tuğ
    0.07
    ResourceManager
    0.06
    _BASIC
    0.06
    форми
    0.06
    chten
    0.06
     mastery
    0.06
     Edited
    0.06
    @"↵
    0.06
    =============↵
    0.06
     tiếng
    0.06
    Act Density 0.005%

    No Known Activations