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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act · gemini-2.0-flash

    technical descriptions related to digital signal processing and circuit design.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    The neuron activates on tokens that are floating-point numeric literals (i.e. numbers with decimal fractions).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     forecasting
    -0.07
    ABLE
    -0.06
    CUR
    -0.06
    _hooks
    -0.06
     FIXED
    -0.06
    fers
    -0.06
    ugged
    -0.06
    cury
    -0.06
    uez
    -0.06
     Gia
    -0.06
    POSITIVE LOGITS
     праці
    0.06
     turmoil
    0.06
    uxt
    0.06
     #↵
    0.06
     респ
    0.06
    .assertNotNull
    0.06
    лаб
    0.06
     typically
    0.06
     postup
    0.06
    ประกอบ
    0.06
    Act Density 0.421%

    No Known Activations