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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash

    chemical compounds used in various industrial applications.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    The neuron activates on occurrences of the word “synthesis,” i.e. it flags mentions of chemical synthesis processes.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ('${
    -0.07
    _Display
    -0.06
    /software
    -0.06
    arp
    -0.06
    дами
    -0.06
    효
    -0.06
     бу
    -0.06
    ồ
    -0.06
     wins
    -0.06
     literacy
    -0.06
    POSITIVE LOGITS
    .binary
    0.07
    Subscriber
    0.07
    Init
    0.07
    检测
    0.07
    ported
    0.07
     aftermarket
    0.06
    .compareTo
    0.06
     ấy
    0.06
     Idol
    0.06
     خبر
    0.06
    Act Density 0.019%

    No Known Activations