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

    Neuronpedia

    INDEX
    Explanations

    weight

    np_max-act · gemini-2.0-flash

    This neuron detects numerical weight measurements (especially pound values and weight limits).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    _gshared
    -0.07
     příst
    -0.06
    (jTextField
    -0.06
     tgt
    -0.06
    STALL
    -0.06
     kne
    -0.06
    ldata
    -0.06
    زه
    -0.06
    Topology
    -0.06
     Maze
    -0.06
    POSITIVE LOGITS
    coln
    0.08
     reck
    0.07
     ensure
    0.07
     forestry
    0.07
    งาน
    0.06
    _Detail
    0.06
     Prov
    0.06
    уди
    0.06
     TIMES
    0.06
    stal
    0.06
    Act Density 0.003%

    No Known Activations