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

    Neuronpedia

    INDEX
    Explanations

    allow

    np_max-act · gemini-2.0-flash

    The neuron responds to words in conditional or potential constructions—i.e. modal language (would, could, allow, enable, etc.) indicating possibility or allowing something.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     che
    -0.06
     Pero
    -0.06
     lest
    -0.06
     sono
    -0.06
    LEC
    -0.06
     اغ
    -0.06
     plastics
    -0.05
    .gstatic
    -0.05
    Coach
    -0.05
    �
    -0.05
    POSITIVE LOGITS
    liv
    0.07
     streamline
    0.07
     Praze
    0.07
     aktu
    0.06
    ละคร
    0.06
     voiced
    0.06
    Sab
    0.06
     Attribute
    0.06
    ,null
    0.06
    Δ
    0.06
    Act Density 0.241%

    No Known Activations