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

    Neuronpedia

    INDEX
    Explanations

    shifting narratives

    np_max-act · gemini-2.0-flash

    The neuron activates on tokens that refer to narrative viewpoint shifts—words like “alternating,” “perspectives,” “shifts,” “POV,” and “narratives.”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     steer
    -0.07
    eon
    -0.07
     баж
    -0.07
    н
    -0.06
    (floor
    -0.06
     timestep
    -0.06
     预
    -0.06
     spotlight
    -0.06
    banks
    -0.06
    @property
    -0.06
    POSITIVE LOGITS
    ===============↵
    0.07
     sterile
    0.07
    _CI
    0.06
    _ar
    0.06
     renk
    0.06
     nominal
    0.06
    iciones
    0.06
     siempre
    0.06
     indirectly
    0.06
    _Main
    0.06
    Act Density 0.046%

    No Known Activations