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

    Neuronpedia

    INDEX
    Explanations

    family

    np_max-act · gemini-2.0-flash

    This neuron identifies the phrase “family of” (and similar classification constructs).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    {(
    -0.07
    んでいる
    -0.06
     فنی
    -0.06
     fu
    -0.06
    ......
    -0.06
     observer
    -0.06
    ParticleSystem
    -0.06
    _Offset
    -0.06
    >}</
    -0.06
    371
    -0.06
    POSITIVE LOGITS
    드
    0.07
     Pokemon
    0.06
    리
    0.06
     الاح
    0.06
     attendees
    0.06
     geç
    0.06
     attn
    0.06
    дет
    0.06
     Todos
    0.06
     ®
    0.06
    Act Density 0.022%

    No Known Activations