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

    Neuronpedia

    INDEX
    Explanations

    materials

    np_max-act · gemini-2.0-flash

    The neuron responds to words naming physical materials or surfaces (e.g. metals, plastics, glass, fibers).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    stride
    -0.07
    (dictionary
    -0.07
     login
    -0.06
    %;
↵
    -0.06
     USER
    -0.06
     SEX
    -0.06
    tz
    -0.06
     testcase
    -0.06
    LOB
    -0.06
    стро
    -0.06
    POSITIVE LOGITS
     інститут
    0.06
     Savaşı
    0.06
    myModalLabel
    0.06
    řila
    0.06
    byn
    0.06
     nợ
    0.06
    ág
    0.06
    sterreich
    0.06
    udo
    0.06
     Gratuit
    0.06
    Act Density 0.032%

    No Known Activations