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

    Neuronpedia

    INDEX
    Explanations

    Production

    np_max-act · gemini-2.0-flash

    This neuron detects section-heading labels (e.g. “Production,” “Release,” “Reception”) in film‐related documents.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     bitterness
    -0.06
    Scene
    -0.06
     Restart
    -0.06
     []*
    -0.06
    _AX
    -0.06
     Kirk
    -0.06
     shelves
    -0.06
    IZ
    -0.06
     три
    -0.06
     HACK
    -0.06
    POSITIVE LOGITS
    rottle
    0.07
    $obj
    0.07
    Sy
    0.07
    πε
    0.06
     Sq
    0.06
    Because
    0.06
    φων
    0.06
     surfaced
    0.06
    umptech
    0.06
    formData
    0.06
    Act Density 0.012%

    No Known Activations