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

    Neuronpedia

    INDEX
    Explanations

    References to papers

    np_max-act · gemini-2.0-flash

    The neuron selectively responds to decimal numerical tokens, i.e. numbers containing a decimal point.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     puppies
    -0.07
     adulthood
    -0.07
    ohan
    -0.07
    Sele
    -0.06
    @hotmail
    -0.06
    .bc
    -0.06
     آرام
    -0.06
    uter
    -0.06
    "));
↵
↵
    -0.06
     buffet
    -0.06
    POSITIVE LOGITS
    ι
    0.07
    전자
    0.07
     SCSI
    0.07
    เฉพาะ
    0.06
    _CANCEL
    0.06
     convenience
    0.06
    \$
    0.06
    ’S
    0.06
     залиш
    0.06
     UNICODE
    0.06
    Act Density 0.003%

    No Known Activations