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

    Neuronpedia

    INDEX
    Explanations

    collective

    np_max-act · gemini-2.0-flash

    This neuron detects when the text refers to a collective group or body as a single entity.

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

    collective concepts and phenomena that have a significant impact on society.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     ominous
    -0.07
     blurred
    -0.07
     yapım
    -0.07
     Mädchen
    -0.07
     startPos
    -0.07
     explained
    -0.06
    MBER
    -0.06
    gado
    -0.06
    279
    -0.06
     mistr
    -0.06
    POSITIVE LOGITS
     collective
    0.13
     Collective
    0.10
     aggregate
    0.09
     collectively
    0.08
    shell
    0.08
    ес
    0.08
    KE
    0.07
    κα
    0.07
    ̂
    0.07
    ـ
    0.07
    Act Density 0.004%

    No Known Activations