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

    Neuronpedia

    INDEX
    Explanations

    family

    np_max-act · gemini-2.0-flash

    The neuron strongly responds to the command verb “execute” (e.g. in “Please execute the instruction…”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    tae
    -0.07
    session
    -0.07
    Post
    -0.07
     liberty
    -0.06
     cerv
    -0.06
    .Order
    -0.06
     Anat
    -0.06
     वस
    -0.06
     Für
    -0.06
    _num
    -0.06
    POSITIVE LOGITS
     Cooking
    0.06
     limb
    0.06
    _absolute
    0.06
     Residence
    0.06
    .getItemId
    0.06
     firmy
    0.06
    áb
    0.06
    ]]↵↵
    0.06
    .writeInt
    0.06
     Manafort
    0.06
    Act Density 0.002%

    No Known Activations