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

    Neuronpedia

    INDEX
    Explanations

    neo

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Harris
    -0.08
    pper
    -0.08
     Wilkinson
    -0.07
    IDD
    -0.07
     Williamson
    -0.07
     Brown
    -0.07
     Murphy
    -0.07
     strán
    -0.07
    burn
    -0.07
    PPER
    -0.07
    POSITIVE LOGITS
     Neo
    0.10
     neo
    0.09
     ne
    0.09
     NEO
    0.09
     Ne
    0.09
    neo
    0.09
    ot
    0.07
     Meg
    0.07
     machine
    0.07
    OTS
    0.07
    Act Density 0.018%

    No Known Activations