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

    Neuronpedia

    INDEX
    Explanations

    .

    np_max-act · gemini-2.0-flash

    The neuron is detecting blank‐line and delimiter regions (paragraph breaks, forwarded‐message separators, and other whitespace‐heavy boundaries) in the email text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     sings
    -0.07
    .assertNotNull
    -0.07
    ��
    -0.07
    °E
    -0.06
    ↵  ↵
    -0.06
    mainwindow
    -0.06
    SDL
    -0.06
    ąd
    -0.06
     dances
    -0.06
     إي
    -0.06
    POSITIVE LOGITS
     PEM
    0.07
    ('./
    0.07
     прост
    0.06
    _published
    0.06
    rootScope
    0.06
    _resize
    0.06
     اجرای
    0.06
     gql
    0.06
    Composite
    0.06
     istedi
    0.06
    Act Density 0.032%

    No Known Activations