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

    Neuronpedia

    INDEX
    Explanations

    Statements/Dialogue

    np_max-act · gemini-2.0-flash

    This neuron primarily responds to first‐person plural pronouns and related collective statements (e.g. “we,” “we’re,” “watching”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    _changes
    -0.06
     (!((
    -0.06
    property
    -0.06
    startTime
    -0.06
    UIAlertAction
    -0.06
    áb
    -0.06
    -anchor
    -0.06
    (fixture
    -0.06
    Що
    -0.06
    explicit
    -0.06
    POSITIVE LOGITS
     wissen
    0.07
     lam
    0.07
     teslim
    0.07
     подк
    0.06
    IZED
    0.06
     Lafayette
    0.06
    MMM
    0.06
    ('</
    0.06
     дела
    0.06
     Cuba
    0.06
    Act Density 0.037%

    No Known Activations