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

    Neuronpedia

    INDEX
    Explanations

    mathematical substitutions

    np_max-act · gemini-2.0-flash

    The neuron flags numeric tokens—especially decimals or other multi‐digit numbers—in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ryfall
    -0.06
    .square
    -0.06
     wolves
    -0.06
    .touches
    -0.06
    ORIES
    -0.06
    ]='
    -0.06
    afa
    -0.06
    데
    -0.06
     Cabr
    -0.06
     Jerseys
    -0.06
    POSITIVE LOGITS
     sow
    0.07
     common
    0.06
    Patients
    0.06
     chronic
    0.06
    Impact
    0.06
    cms
    0.06
    -action
    0.06
    meric
    0.06
    _resize
    0.06
    duced
    0.06
    Act Density 0.022%

    No Known Activations