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

    Neuronpedia

    INDEX
    Explanations

    correct

    np_max-act · gemini-2.0-flash

    The neuron detects words and phrases that indicate the correction or adjustment of measurements or data.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    니스
    -0.07
    IXEL
    -0.06
    arem
    -0.06
    Recipes
    -0.06
    /company
    -0.06
    ammer
    -0.06
     anno
    -0.06
    сяг
    -0.06
    私は
    -0.06
    anye
    -0.05
    POSITIVE LOGITS
    163
    0.07
     الدولة
    0.07
     TED
    0.07
    055
    0.07
    698
    0.06
     home
    0.06
    927
    0.06
     факт
    0.06
     esac
    0.06
    402
    0.06
    Act Density 0.026%

    No Known Activations