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

    Neuronpedia

    INDEX
    Explanations

    Car

    np_max-act · gemini-2.0-flash

    The neuron specifically detects occurrences of the subtoken “Car,” i.e. the prefix “Car” at the start of words.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    [port
    -0.06
     Europa
    -0.06
    	INNER
    -0.06
    ého
    -0.06
    .Mail
    -0.06
     χρό
    -0.06
    ("~/
    -0.06
     oli
    -0.06
     YM
    -0.06
    orders
    -0.06
    POSITIVE LOGITS
    patible
    0.07
    。。↵↵
    0.07
    rollback
    0.06
    рукт
    0.06
    .setBackgroundColor
    0.06
    _encode
    0.06
    ffiti
    0.06
    _IF
    0.06
    #↵
    0.06
     volcanic
    0.06
    Act Density 0.020%

    No Known Activations