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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash

    This neuron activates on numeric literals with decimal points (i.e. floating‐point numbers).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     collabor
    -0.07
    liğ
    -0.06
    _DOUBLE
    -0.06
     оптим
    -0.06
    _META
    -0.06
    https
    -0.06
    ันออก
    -0.06
    狐
    -0.06
    ocs
    -0.06
     tourist
    -0.06
    POSITIVE LOGITS
    'é
    0.06
    analytics
    0.06
    .opensource
    0.06
    -vis
    0.06
     mü
    0.06
    ProgressDialog
    0.06
    재
    0.06
    クラブ
    0.06
     přece
    0.06
    mae
    0.06
    Act Density 0.082%

    No Known Activations