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

    Neuronpedia

    INDEX
    Explanations

    interrogation

    np_max-act · gemini-2.0-flash

    The neuron activates on occurrences of “interrogation,” “torture,” and related terms (especially in the context of interrogation techniques or memos).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     الخط
    -0.08
    .embed
    -0.06
    会
    -0.06
     mixer
    -0.06
    ipi
    -0.06
     Valentine
    -0.06
    ตะ
    -0.06
     όπως
    -0.06
    ANGED
    -0.06
    Cont
    -0.06
    POSITIVE LOGITS
     імен
    0.07
    обов
    0.06
     &[
    0.06
     strategies
    0.06
     primaryKey
    0.06
     comparisons
    0.06
     ngOnInit
    0.06
    .rawValue
    0.06
    refix
    0.06
     fixation
    0.06
    Act Density 0.004%

    No Known Activations