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

    Neuronpedia

    INDEX
    Explanations

    ated

    np_max-act · gemini-2.0-flash

    This neuron detects mentions of dilation (e.g., “dilated,” “dilatation”) in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     //////
    -0.08
     unbe
    -0.07
     کوچ
    -0.06
     expected
    -0.06
     Cu
    -0.06
     methods
    -0.06
     متحده
    -0.06
     Pb
    -0.06
     jste
    -0.06
    �
    -0.06
    POSITIVE LOGITS
     dilation
    0.11
    efs
    0.07
     widening
    0.07
     Platinum
    0.07
     воспал
    0.07
     Diana
    0.07
     Dana
    0.07
     open
    0.07
     dil
    0.07
    panse
    0.07
    Act Density 0.003%

    No Known Activations