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

    Neuronpedia

    INDEX
    Explanations

    our

    np_max-act · gemini-2.0-flash

    This neuron primarily activates on first-person pronouns and possessive forms (e.g. “I,” “my,” “our”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    _PC
    -0.07
     Resource
    -0.07
     phot
    -0.07
     cancer
    -0.07
     capitalism
    -0.07
     взаим
    -0.07
    IRECTION
    -0.07
    -ahead
    -0.07
     Fully
    -0.07
     Send
    -0.07
    POSITIVE LOGITS
    者
    0.06
     heirs
    0.06
    ущ
    0.06
    ağa
    0.06
    :@{
    0.06
    ={$
    0.06
    clicked
    0.06
     primeira
    0.06
    ΩΣ
    0.06
    azor
    0.06
    Act Density 0.152%

    No Known Activations