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

    Neuronpedia

    INDEX
    Explanations

    and

    np_max-act · gemini-2.0-flash

    The neuron activates on decimal numeral tokens (e.g., floating‐point numbers).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    .CurrentRow
    -0.07
    ��️
    -0.07
    ��
    -0.06
    ".$
    -0.06
    _TB
    -0.06
    Bat
    -0.06
    >",↵
    -0.06
    ूबर
    -0.06
    Chars
    -0.06
    دة
    -0.06
    POSITIVE LOGITS
     or
    0.08
     mechan
    0.07
     eag
    0.07
    eyed
    0.07
     tort
    0.07
     and
    0.07
    .nlm
    0.07
     conco
    0.06
    -tool
    0.06
     melts
    0.06
    Act Density 0.135%

    No Known Activations