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

    Neuronpedia

    INDEX
    Explanations

    Mathematics

    np_max-act · gemini-2.0-flash

    The neuron fires on occurrences of the symbol “k” with a subscript (e.g. k₁, k₂, k_i) in mathematical expressions.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    adlo
    -0.07
    γου
    -0.07
    levision
    -0.07
    reta
    -0.07
    ců
    -0.06
    الح
    -0.06
    пеки
    -0.06
     التف
    -0.06
    vä
    -0.06
    ographic
    -0.06
    POSITIVE LOGITS
     hub
    0.07
     Substitute
    0.07
    Timer
    0.07
     Helps
    0.06
     Plans
    0.06
     Infer
    0.06
     Secure
    0.06
    ₀
    0.06
     overflow
    0.06
     UTIL
    0.06
    Act Density 0.017%

    No Known Activations