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

    Neuronpedia

    INDEX
    Explanations

    descriptions

    np_max-act · gemini-2.0-flash

    The neuron flags warnings or cautions describing bright or flashing visual stimuli that may cause discomfort or adverse effects.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     dissemination
    -0.06
     Transmission
    -0.06
     arbitration
    -0.06
     apolog
    -0.06
    (client
    -0.06
     sync
    -0.06
    (training
    -0.06
    (post
    -0.06
     prune
    -0.06
     Layer
    -0.06
    POSITIVE LOGITS
    ��
    0.07
     Mah
    0.06
    /db
    0.06
    лара
    0.06
     OSI
    0.06
    CAA
    0.06
    miyor
    0.06
    !'
    0.06
    QRS
    0.06
    -pro
    0.06
    Act Density 0.069%

    No Known Activations