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

    Neuronpedia

    INDEX
    Explanations

    :

    np_max-act · gemini-2.0-flash

    This neuron spots software‐license header blocks (e.g. copyright and license notice sections).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     sice
    -0.07
    _Equals
    -0.07
     )))
    -0.06
    phies
    -0.06
    28
    -0.06
    Real
    -0.06
    oki
    -0.06
    )))
    -0.06
     良
    -0.06
     Electric
    -0.06
    POSITIVE LOGITS
     ordinances
    0.07
     emploi
    0.07
    tot
    0.07
    -economic
    0.07
     で
    0.06
    泥
    0.06
    сят
    0.06
     вули
    0.06
    uator
    0.06
    buquerque
    0.06
    Act Density 0.017%

    No Known Activations