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

    Neuronpedia

    INDEX
    Explanations

    energy reliability

    np_max-act · gemini-2.0-flash

    The neuron fires on the headings or labels of numbered list items (e.g. "Availability," "Reliability," "Flexibility") in a structured comparison.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    	pop
    -0.07
    출장마사지
    -0.06
     günü
    -0.06
    Assignable
    -0.06
     Dialogue
    -0.06
     fort
    -0.06
    Buff
    -0.06
    atoire
    -0.06
    ")}
    -0.06
     Passage
    -0.06
    POSITIVE LOGITS
    ashes
    0.06
    يدي
    0.06
     đáng
    0.06
    Birth
    0.06
     Eli
    0.06
     elast
    0.06
     Rew
    0.06
     Cec
    0.06
    ี
    0.06
     όλα
    0.06
    Act Density 0.008%

    No Known Activations