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

    Neuronpedia

    INDEX
    Explanations

    code/technical documentation

    np_max-act · gemini-2.0-flash

    The neuron is primarily triggered by occurrences of the short function word “in.”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ofs
    -0.07
     manager
    -0.07
     nelle
    -0.07
     dad
    -0.07
     friend
    -0.07
     bitterness
    -0.06
     Tester
    -0.06
    .oper
    -0.06
    ackages
    -0.06
    ))):↵
    -0.06
    POSITIVE LOGITS
    ีช
    0.07
    刑
    0.06
     يمكن
    0.06
    افع
    0.06
    urovision
    0.06
     '_
    0.06
     вероят
    0.06
     huge
    0.06
    emales
    0.06
    ेव
    0.06
    Act Density 0.120%

    No Known Activations