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

    Neuronpedia

    INDEX
    Explanations

    Informal instructions/text

    np_max-act · gemini-2.0-flash

    The neuron activates on language about acquiring or exerting power, control, influence, or dominance.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    의
    -0.07
     اخبار
    -0.06
    „V
    -0.06
    _readable
    -0.06
    盟
    -0.06
    Ｏ
    -0.06
     Finch
    -0.06
     �
    -0.06
    EY
    -0.06
     referencia
    -0.06
    POSITIVE LOGITS
     gym
    0.06
    hawks
    0.06
    amura
    0.06
    -bs
    0.06
    .algorithm
    0.06
    tenant
    0.06
    caff
    0.06
     jazz
    0.06
    res
    0.06
    。“
    0.06
    Act Density 0.035%

    No Known Activations