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

    Neuronpedia

    INDEX
    Explanations

    is

    np_max-act · gemini-2.0-flash

    This neuron primarily detects “this is …” constructions used to introduce a summary or evaluative statement.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    izzare
    -0.07
    -db
    -0.06
    ３
    -0.06
    HIR
    -0.06
    احت
    -0.06
    _it
    -0.06
    acı
    -0.06
     itinerary
    -0.06
    -i
    -0.06
    اوری
    -0.06
    POSITIVE LOGITS
    .Size
    0.07
    ổi
    0.07
    /vendor
    0.06
    .fullName
    0.06
     loses
    0.06
     ناب
    0.06
     admin
    0.06
    _mail
    0.06
    acağını
    0.06
     fights
    0.06
    Act Density 0.057%

    No Known Activations