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

    Neuronpedia

    INDEX
    Explanations

    positive sentiment

    np_max-act · gemini-2.0-flash

    This neuron fires on subjective, evaluative words conveying positive or negative sentiment (e.g., “good,” “happy,” “fun,” “bad”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Cancer
    -0.08
     Kem
    -0.07
    \<
    -0.07
     employs
    -0.07
     equivalence
    -0.06
     Friday
    -0.06
     diversity
    -0.06
     ترین
    -0.06
     enough
    -0.06
    	R
    -0.06
    POSITIVE LOGITS
    regs
    0.07
    WithType
    0.07
    说明
    0.07
     DEBUG
    0.06
    Rect
    0.06
    itm
    0.06
     abusing
    0.06
    CGPoint
    0.06
     soo
    0.06
     lå
    0.06
    Act Density 0.049%

    No Known Activations