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

    Neuronpedia

    INDEX
    Explanations

    2

    np_max-act · gemini-2.0-flash

    This neuron detects technical or mathematical terminology—especially words relating to optimization concepts like “optimizes,” “distances,” “augmentation term,” and “objectives.”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     spree
    -0.07
    しか
    -0.07
     된다
    -0.07
    Chan
    -0.06
     analogy
    -0.06
    Inserted
    -0.06
    .StackTrace
    -0.06
    ):(
    -0.06
    ところ
    -0.06
    .Car
    -0.06
    POSITIVE LOGITS
    �
    0.07
     поверхность
    0.07
     gene
    0.06
    \F
    0.06
    chunks
    0.06
     Gl
    0.06
     =&
    0.06
     hızlı
    0.06
    /html
    0.06
    |;↵
    0.06
    Act Density 0.007%

    No Known Activations