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

    Neuronpedia

    INDEX
    Explanations

    programming and networks

    np_max-act · gemini-2.0-flash

    The neuron is detecting ASCII-art drawing characters and symbols used to compose line‐based diagrams.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    Lists
    -0.07
    τολ
    -0.07
     Built
    -0.07
    IGNORE
    -0.07
    fig
    -0.06
     zů
    -0.06
    liğine
    -0.06
    SAMPLE
    -0.06
    图
    -0.06
    	ti
    -0.06
    POSITIVE LOGITS
     στην
    0.07
     объем
    0.06
    -any
    0.06
     Prevent
    0.06
     cervical
    0.06
     visa
    0.06
     उद
    0.06
     sack
    0.06
     rise
    0.06
    /is
    0.05
    Act Density 0.009%

    No Known Activations