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

    Neuronpedia

    INDEX
    Explanations

    email

    np_max-act · gemini-2.0-flash

    the neuron detects mentions of email communications (e-mail, email, blast, forward(ed), forwarding)

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     지난
    -0.06
    相关
    -0.06
    eterangan
    -0.06
    běhu
    -0.06
    gtest
    -0.06
     bustling
    -0.06
    фі
    -0.06
    afe
    -0.06
     NASCAR
    -0.06
     Orlando
    -0.06
    POSITIVE LOGITS
    tu
    0.07
    instanc
    0.06
    ige
    0.06
    iga
    0.06
    chor
    0.06
     Email
    0.06
    Compilation
    0.06
     mdb
    0.06
     Sant
    0.06
     imb
    0.05
    Act Density 0.016%

    No Known Activations