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

    Neuronpedia

    INDEX
    Explanations

    percentages and numbers

    np_max-act · gemini-2.0-flash

    This neuron activates on numeric tokens (digits and figures), especially percentages and other numerical values.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    цей
    -0.07
     azi
    -0.07
    _USED
    -0.07
     nationalists
    -0.07
    еня
    -0.07
     transporter
    -0.06
     Tax
    -0.06
     broader
    -0.06
    807
    -0.06
    ака
    -0.06
    POSITIVE LOGITS
     trava
    0.07
     rumor
    0.06
     поки
    0.06
     перс
    0.06
     repairing
    0.06
     znamená
    0.06
     �
    0.06
    �
    0.06
     aesthetic
    0.06
    ActivityCreated
    0.06
    Act Density 0.016%

    No Known Activations