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 containing decimal points.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     random
    -0.07
    pto
    -0.06
     malicious
    -0.06
    136
    -0.06
     baud
    -0.06
     Orn
    -0.06
     ACCESS
    -0.06
     Aviv
    -0.06
    implements
    -0.06
     div
    -0.06
    POSITIVE LOGITS
    .recipe
    0.07
    웨디시
    0.07
     побед
    0.06
    contres
    0.06
     अगल
    0.06
     위한
    0.06
    =fopen
    0.06
    went
    0.06
    düğ
    0.06
    لسل
    0.06
    Act Density 0.033%

    No Known Activations