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

    Neuronpedia

    INDEX
    Explanations

    phone numbers

    np_max-act · gemini-2.0-flash

    The neuron activates on numeric tokens—especially sequences of digits in contact details like phone numbers.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    άλ
    -0.07
    ngrx
    -0.07
     />,↵
    -0.06
    ¡
    -0.06
    	td
    -0.06
    709
    -0.06
    INVAL
    -0.06
    909
    -0.06
    Mas
    -0.06
    ตำ
    -0.06
    POSITIVE LOGITS
     cleanly
    0.07
     Cartoon
    0.07
    adopt
    0.07
     우리
    0.06
     Presents
    0.06
     Candidates
    0.06
     MARK
    0.06
    lsru
    0.06
     الملك
    0.06
    why
    0.06
    Act Density 0.009%

    No Known Activations