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

    Neuronpedia

    INDEX
    Explanations

    Start of fiction

    np_max-act · gemini-2.0-flash

    The neuron chiefly responds to words that describe internal sensations or emotional states (e.g., “sense,” “deep,” “feeling,” “tension”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    RESSION
    -0.07
    GR
    -0.07
    mirror
    -0.07
    ipple
    -0.06
    	entry
    -0.06
    taken
    -0.06
     ecosystems
    -0.06
    route
    -0.06
     ventilation
    -0.06
    (window
    -0.06
    POSITIVE LOGITS
    [class
    0.07
     contrario
    0.06
    .Rotate
    0.06
     effic
    0.06
    /code
    0.06
    ."[
    0.06
    اك
    0.06
    YM
    0.06
     She
    0.06
     Rising
    0.06
    Act Density 0.065%

    No Known Activations