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

    Neuronpedia

    INDEX
    Explanations

    district

    np_max-act · gemini-2.0-flash

    The neuron is primarily triggered by numeric tokens, including digits and decimal‐formatted numbers.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     bullshit
    -0.06
     unread
    -0.06
     discrimination
    -0.06
     Scientology
    -0.06
     Started
    -0.06
    ，她
    -0.06
    ‌پدیای
    -0.06
    ollections
    -0.06
    بين
    -0.06
     alg
    -0.06
    POSITIVE LOGITS
     ود
    0.07
    enticate
    0.06
    ують
    0.06
    太阳城
    0.06
     đầu
    0.06
    _sd
    0.06
    衝
    0.06
    
    0.06
    .positions
    0.06
     Boise
    0.06
    Act Density 0.009%

    No Known Activations