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

    Neuronpedia

    INDEX
    Explanations

    auxiliary verbs

    np_max-act · gemini-2.0-flash

    The neuron detects phrasing that assigns blame or credit by using “the one who …” constructions (e.g. “Stuart was the one who made the mistake”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     '../../../
    -0.07
    currentUser
    -0.06
    �
    -0.06
    ETF
    -0.06
    ffd
    -0.06
    [D
    -0.06
    842
    -0.06
    <Element
    -0.06
     дер
    -0.06
     IoT
    -0.06
    POSITIVE LOGITS
    _MP
    0.07
    .channels
    0.07
     damit
    0.07
     hab
    0.06
     printable
    0.06
    ภายใน
    0.06
     environments
    0.06
    él
    0.06
    صل
    0.06
    ánd
    0.06
    Act Density 0.086%

    No Known Activations