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

    Neuronpedia

    INDEX
    Explanations

    mood

    np_max-act · gemini-2.0-flash

    text that discusses mental health issues related to stress and anxiety.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    The neuron consistently activates on occurrences of the word “mood.”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     взя
    -0.07
     Особ
    -0.07
    ण
    -0.07
    izyon
    -0.07
     техничес
    -0.07
     деревян
    -0.07
     particle
    -0.07
     Taş
    -0.07
    anganese
    -0.07
    alan
    -0.06
    POSITIVE LOGITS
     mood
    0.16
     Mood
    0.12
     bladder
    0.08
     Moody
    0.08
     �
    0.07
     spirits
    0.07
     Moor
    0.07
    	SP
    0.07
     Temper
    0.07
     MMI
    0.07
    Act Density 0.005%

    No Known Activations