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

    Neuronpedia

    INDEX
    Explanations

    black holes

    np_max-act · gemini-2.0-flash

    The neuron is primarily activated by Spanish-language text segments.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    	struct
    -0.08
    396
    -0.07
    /software
    -0.07
    IELDS
    -0.06
    agnostic
    -0.06
    representation
    -0.06
    บก
    -0.06
    .xml
    -0.06
    ahead
    -0.06
     entrepreneurial
    -0.06
    POSITIVE LOGITS
     дом
    0.07
     sexually
    0.06
     환경
    0.06
     hàng
    0.06
     Throughout
    0.06
     Shortcut
    0.05
    aria
    0.05
    .SET
    0.05
    ilename
    0.05
    �
    0.05
    Act Density 0.015%

    No Known Activations