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

    Neuronpedia

    INDEX
    Explanations

    shield

    np_max-act · gemini-2.0-flash

    The neuron activates on occurrences of the word “shield” (including its morphological variants like “shielded” or “shielding”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    	time
    -0.07
    (date
    -0.07
     �
    -0.07
    Time
    -0.07
    Become
    -0.07
    �
    -0.07
    aturday
    -0.07
    Numer
    -0.07
    Vari
    -0.07
    ago
    -0.06
    POSITIVE LOGITS
     shield
    0.17
     Shield
    0.15
    Shield
    0.13
     shields
    0.12
     Shields
    0.10
     shielding
    0.09
    shield
    0.08
     Nichols
    0.08
     chip
    0.07
    ////////////////////////////////////////////////////
    0.07
    Act Density 0.003%

    No Known Activations