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

    Neuronpedia

    INDEX
    Explanations

    innovation

    np_max-act · gemini-2.0-flash

    The neuron selectively activates on the word “innovation.”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    '||
    -0.06
     scholarly
    -0.06
    лоп
    -0.06
    .LogError
    -0.06
    _snap
    -0.06
     sph
    -0.06
    (face
    -0.06
    궁
    -0.06
    _TCP
    -0.06
     Hồng
    -0.06
    POSITIVE LOGITS
    _require
    0.07
    forall
    0.07
    ーテ
    0.07
     imply
    0.06
     predicts
    0.06
    omination
    0.06
    صب
    0.06
    }/${
    0.06
    @author
    0.06
     banning
    0.06
    Act Density 0.013%

    No Known Activations