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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash

    This neuron activates on programming-style syntax (code tokens and punctuation), effectively detecting source-code segments in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    英語
    -0.07
    mj
    -0.07
    Descriptions
    -0.07
    _sr
    -0.07
     meer
    -0.07
    amburger
    -0.06
    تمر
    -0.06
    كيل
    -0.06
    人类
    -0.06
    halb
    -0.06
    POSITIVE LOGITS
    156
    0.07
     artic
    0.06
    oooo
    0.06
    159
    0.06
     hesitate
    0.06
     hect
    0.06
    ];↵↵
    0.06
    ={()=>
    0.06
    194
    0.06
    178
    0.06
    Act Density 0.019%

    No Known Activations