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

    Neuronpedia

    INDEX
    Explanations

    hereditary inherited

    np_max-act · gemini-2.0-flash

    The neuron selectively activates on terms indicating genetic inheritance—especially words like “hereditary,” “inherited,” or closely related descriptors of inherited disorders.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    parency
    -0.07
     Mesh
    -0.07
    更加
    -0.07
     Pink
    -0.06
    _pin
    -0.06
    .Logger
    -0.06
     Transparency
    -0.06
     Programme
    -0.06
    .nc
    -0.06
    tel
    -0.06
    POSITIVE LOGITS
     Faster
    0.07
     cease
    0.06
     whoever
    0.06
     volunteers
    0.06
    ！
    0.06
     inevitably
    0.06
    Advice
    0.06
    _CHOICES
    0.06
     初始化
    0.06
     shorter
    0.06
    Act Density 0.006%

    No Known Activations