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

    Neuronpedia

    INDEX
    Explanations

    drafting and developing

    np_max-act · gemini-2.0-flash

    The main thing this neuron does is detect language describing the formulation or drafting of formal documents, policies, regulations, or plans.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    控制
    -0.06
     말을
    -0.06
    _OPTION
    -0.06
     behave
    -0.06
     IGNORE
    -0.06
    átek
    -0.06
    PathVariable
    -0.06
     pattern
    -0.06
    ojí
    -0.05
    위를
    -0.05
    POSITIVE LOGITS
     rough
    0.07
     nominate
    0.07
     yapım
    0.07
    ere
    0.06
    製作
    0.06
     hemp
    0.06
    otonin
    0.06
    .conn
    0.06
     Rew
    0.06
    0.06
    Act Density 0.029%

    No Known Activations