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

    Neuronpedia

    INDEX
    Explanations

    like

    np_max-act · gemini-2.0-flash

    The main thing this neuron does is detect the filler/comparative word “like” in text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ulnerable
    -0.07
     ضو
    -0.06
    zym
    -0.06
    .activity
    -0.06
     koruy
    -0.06
     sebuah
    -0.06
     sclerosis
    -0.06
    	info
    -0.06
     festivals
    -0.06
    河
    -0.06
    POSITIVE LOGITS
     Like
    0.08
     Shard
    0.08
    .console
    0.07
     لي
    0.07
    。”↵↵
    0.06
    
    0.06
    Like
    0.06
     ارد
    0.06
     habit
    0.06
    请选择
    0.06
    Act Density 0.015%

    No Known Activations