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

    Neuronpedia

    INDEX
    Explanations

    hal

    np_max-act · gemini-2.0-flash

    The neuron detects technical orthodontic terminology, especially skeletal classifications (e.g. Class II/III malocclusion) and accompanying cephalometric measurement language.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     等
    -0.06
     spiders
    -0.06
    rael
    -0.06
    ařilo
    -0.06
     preserving
    -0.06
     letters
    -0.06
    ECH
    -0.06
    740
    -0.06
    Crypto
    -0.05
     ancor
    -0.05
    POSITIVE LOGITS
    _dc
    0.07
     utilization
    0.07
    _channel
    0.07
    τών
    0.06
    _ac
    0.06
     فريق
    0.06
    ัพ
    0.06
     розум
    0.06
    .Role
    0.06
     Giles
    0.06
    Act Density 0.005%

    No Known Activations