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

    Neuronpedia

    INDEX
    Explanations

    name origins

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ('/
    -0.06
     Sofa
    -0.06
     attractive
    -0.06
     unread
    -0.06
     cheers
    -0.06
    きた
    -0.06
     climate
    -0.06
    datal
    -0.06
     began
    -0.06
    Owner
    -0.06
    POSITIVE LOGITS
    phy
    0.07
    _ylabel
    0.07
     ชนะ
    0.07
    jected
    0.07
    639
    0.06
    失败
    0.06
     dood
    0.06
    <Guid
    0.06
     wxString
    0.06
     nghề
    0.06
    Act Density 0.030%

    No Known Activations