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

    Neuronpedia

    INDEX
    Explanations

    definitions and explanations

    np_max-act · gemini-2.0-flash

    The neuron fires on section‐heading and list‐item markers (e.g. “Some key aspects,” numbered list tokens, and related introductory phrases).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    谁
    -0.06
    _given
    -0.06
    .OPEN
    -0.06
     pitched
    -0.06
     dynamically
    -0.06
    Notice
    -0.06
    FontSize
    -0.06
     Seeing
    -0.06
     Autor
    -0.06
     surface
    -0.06
    POSITIVE LOGITS
    (tableName
    0.07
     chooser
    0.07
    ορ
    0.06
     kì
    0.06
     transcript
    0.06
    ného
    0.06
     transmission
    0.06
    \$
    0.06
    ->{'
    0.06
     Федера
    0.06
    Act Density 0.089%

    No Known Activations