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

    Neuronpedia

    INDEX
    Explanations

    about

    np_max-act · gemini-2.0-flash

    The neuron responds to bits of first-person, self-reflective or experiential language—i.e. “I … learned,” “I’m excited about…,” “I wonder if…,” and similar personal-narrative phrasing.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Mart
    -0.07
     LOGGER
    -0.06
    bote
    -0.06
     template
    -0.06
     Registrar
    -0.06
     pom
    -0.06
    'utilisation
    -0.06
     detal
    -0.06
    "{
    -0.06
     Sum
    -0.06
    POSITIVE LOGITS
     uygu
    0.06
    social
    0.06
    RET
    0.06
    (',')↵
    0.06
     ASE
    0.06
    kish
    0.06
    formatted
    0.06
     horrifying
    0.06
     steroids
    0.06
    ональ
    0.06
    Act Density 0.113%

    No Known Activations