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

    Neuronpedia

    INDEX
    Explanations

    points

    np_max-act · gemini-2.0-flash

    This neuron activates on the term “points” (and its Spanish equivalent “puntos”) when users ask for numbered or bulleted list items.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    _();↵
    -0.07
     mulher
    -0.07
     cbo
    -0.06
    _stdout
    -0.06
     },
↵
    -0.06
     >
↵
    -0.06
    	tp
    -0.06
    าจาก
    -0.06
    bairro
    -0.05
    ูกค
    -0.05
    POSITIVE LOGITS
     Points
    0.08
     Point
    0.08
     points
    0.07
     advis
    0.07
    -points
    0.07
    .WaitFor
    0.07
    ۲۱
    0.07
     Uh
    0.07
    epy
    0.07
     point
    0.07
    Act Density 0.013%

    No Known Activations