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

    Neuronpedia

    INDEX
    Explanations

    Asking questions

    np_max-act · gemini-2.0-flash

    This neuron fires on question‐asking phrases—particularly the “How can I …?” pattern (and the answer label “A:” that follows).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    兴
    -0.07
     sollten
    -0.07
     Instantiate
    -0.06
     EnumerableStream
    -0.06
       
↵
    -0.06
     =============================================================================↵
    -0.06
    ucid
    -0.06
     мінім
    -0.06
     CGPoint
    -0.06
    俺は
    -0.06
    POSITIVE LOGITS
    (cols
    0.07
    к
    0.07
     hur
    0.06
    ουργ
    0.06
     locate
    0.06
    .ImageView
    0.06
    DH
    0.06
    ¼
    0.06
     packing
    0.06
    努力
    0.06
    Act Density 0.105%

    No Known Activations