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

    Neuronpedia

    INDEX
    Explanations

    comma

    np_max-act · gemini-2.0-flash

    The neuron strongly activates on the third-person plural pronoun “they.”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    !='
    -0.06
     Growth
    -0.06
    =@"
    -0.06
    AppBar
    -0.06
          
    -0.06
    ávají
    -0.06
    h
    -0.06
    '>"
    -0.06
     pazar
    -0.06
    Examples
    -0.06
    POSITIVE LOGITS
     Vice
    0.07
     conced
    0.06
    separator
    0.06
     renderItem
    0.06
     atención
    0.06
    emic
    0.06
    原始
    0.06
    RGBO
    0.06
    want
    0.06
    likelihood
    0.06
    Act Density 0.031%

    No Known Activations