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

    Neuronpedia

    INDEX
    Explanations

    by

    np_max-act · gemini-2.0-flash

    The neuron detects instances of the phrase “driven by,” flagging texts that introduce a motivating cause or agent.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    	std
    -0.08
     состав
    -0.08
    _for
    -0.07
    (fout
    -0.07
    ِه
    -0.07
     slag
    -0.07
    roken
    -0.07
     logout
    -0.07
    urança
    -0.07
     στον
    -0.07
    POSITIVE LOGITS
     These
    0.07
     Forge
    0.07
     governed
    0.06
    Certain
    0.06
    BB
    0.06
    piration
    0.06
     روشن
    0.06
     mystical
    0.06
    -looking
    0.06
     Bright
    0.06
    Act Density 0.020%

    No Known Activations