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

    Neuronpedia

    INDEX
    Explanations

    circle

    np_max-act · gemini-2.0-flash

    This neuron activates on words describing geometric shapes or forms (e.g., circle, triangular, rectangular, elliptical).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     situ
    -0.07
     Hick
    -0.07
    效
    -0.07
    (auto
    -0.06
    avan
    -0.06
     bricks
    -0.06
    ’l
    -0.06
    _UNDEF
    -0.06
    #ifndef
    -0.06
    (stats
    -0.06
    POSITIVE LOGITS
    NotFoundException
    0.08
    .functions
    0.06
     appearing
    0.06
     vin
    0.06
    .generated
    0.06
     Druh
    0.06
    ction
    0.06
    名称
    0.06
    нт
    0.06
    .pag
    0.06
    Act Density 0.010%

    No Known Activations