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

    Neuronpedia

    INDEX
    Explanations

    serious

    np_max-act · gemini-2.0-flash

    The neuron flags serious, formal language—especially terms you’d find in a legal or courtroom context.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8

    situations involving absurd or comical interactions, particularly in a military or confrontational context.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     maintenant
    -0.07
    —at
    -0.07
     Nep
    -0.07
     Administrative
    -0.06
    μμα
    -0.06
    arin
    -0.06
     μα
    -0.06
    ure
    -0.06
    812
    -0.06
     connect
    -0.06
    POSITIVE LOGITS
     yogurt
    0.06
     stacks
    0.06
    (sc
    0.06
    getClass
    0.06
    줄
    0.06
    >{"
    0.06
     yapıl
    0.06
     swearing
    0.06
     datum
    0.06
    .QLabel
    0.06
    Act Density 0.114%

    No Known Activations