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

    Neuronpedia

    INDEX
    Explanations

    Images

    np_max-act · gemini-2.0-flash

    This neuron fires on tokens referring to still-image media (e.g. “picture,” “pics,” “photo”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    _sink
    -0.07
     Nazis
    -0.07
    ITT
    -0.06
    PlainOldData
    -0.06
    :length
    -0.06
    esehen
    -0.06
     موس
    -0.06
     الموس
    -0.06
    Doctor
    -0.06
    Usu
    -0.06
    POSITIVE LOGITS
     вв
    0.07
     cer
    0.07
     aberr
    0.07
     Πλη
    0.07
     силь
    0.07
    回
    0.07
    起
    0.07
     photos
    0.06
    .jpeg
    0.06
    happy
    0.06
    Act Density 0.100%

    No Known Activations