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

    Neuronpedia

    INDEX
    Explanations

    manipulate

    np_max-act · gemini-2.0-flash

    The neuron selectively activates on the verb “manipulate” (and its inflected forms like “manipulating”), flagging occurrences of that word.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     професій
    -0.06
     cortical
    -0.06
    edium
    -0.06
    ortality
    -0.06
    lications
    -0.06
     focal
    -0.06
     Scott
    -0.06
     horrific
    -0.06
     ecosystems
    -0.06
    licted
    -0.06
    POSITIVE LOGITS
     manipulation
    0.12
     manip
    0.12
     Manip
    0.11
     manipulated
    0.10
    Manip
    0.09
     manipulating
    0.09
     manipulate
    0.08
     [...]
    0.08
     Manning
    0.07
    operate
    0.07
    Act Density 0.010%

    No Known Activations