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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash

    This neuron detects numeric tokens (including integers and decimal numbers) and basic arithmetic symbols in mathematical equations.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Mov
    -0.07
     Zack
    -0.07
     Gerald
    -0.07
    ым
    -0.06
     IEEE
    -0.06
     negotiations
    -0.06
     marsh
    -0.06
     texto
    -0.06
     fou
    -0.06
     piano
    -0.06
    POSITIVE LOGITS
    -admin
    0.06
     ALLOW
    0.06
    ีพ
    0.06
     conditioning
    0.06
    king
    0.06
     ◄
    0.06
     brushing
    0.06
    �
    0.06
     splitting
    0.06
    -blocking
    0.06
    Act Density 0.013%

    No Known Activations