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

    Neuronpedia

    INDEX
    Explanations

    tests and evaluation

    np_max-act · gemini-2.0-flash

    The neuron detects verbs and phrases that introduce the quantitative measurement or assessment of study variables.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    tic
    -0.06
     Floors
    -0.06
     abound
    -0.06
    اوند
    -0.06
     Wisdom
    -0.06
     کنار
    -0.06
    _heap
    -0.06
     Bucket
    -0.06
    くの
    -0.06
    (error
    -0.05
    POSITIVE LOGITS
    ennent
    0.07
    (CON
    0.07
    威
    0.07
    .har
    0.07
    伊
    0.06
    redient
    0.06
    (create
    0.06
    Phi
    0.06
     prat
    0.06
     ava
    0.06
    Act Density 0.018%

    No Known Activations