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

    Neuronpedia

    INDEX
    Explanations

    └

    np_max-act · gemini-2.0-flash

    The neuron detects ASCII directory‐tree drawing characters (e.g. “└”, “──”, “│”) in code or text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ーデ
    -0.07
    req
    -0.07
    .cert
    -0.06
    [_
    -0.06
    udget
    -0.06
    	x
    -0.06
    /store
    -0.06
    Sec
    -0.06
     Beard
    -0.06
    451
    -0.06
    POSITIVE LOGITS
     защ
    0.07
    statusCode
    0.07
     ├──
    0.07
    ."<
    0.07
    ┣
    0.06
     '".$
    0.06
    μβρίου
    0.06
    Lt
    0.06
    �
    0.06
     ├
    0.06
    Act Density 0.002%

    No Known Activations