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

    Neuronpedia

    INDEX
    Explanations

    feelings and emotions

    np_max-act · gemini-2.0-flash

    The neuron activates on words describing human instincts, emotional or psychological reactions (e.g., “reaction,” “natural,” “urge,” “psychology”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     suitable
    -0.07
     ///
    -0.06
     fragmented
    -0.06
    Creature
    -0.06
     IndexError
    -0.06
     stationary
    -0.06
    ielding
    -0.06
    !="
    -0.06
    belongsTo
    -0.06
     juego
    -0.06
    POSITIVE LOGITS
    .blog
    0.07
    итор
    0.07
     جم
    0.07
    cooked
    0.07
    rob
    0.06
    ,))↵
    0.06
     εγκα
    0.06
     romant
    0.06
    Coupon
    0.06
    λι
    0.06
    Act Density 0.060%

    No Known Activations