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

    Neuronpedia

    INDEX
    Explanations

    Code and technical content

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    addAction
    -0.06
    ematik
    -0.06
     deserving
    -0.06
    ianne
    -0.06
    anness
    -0.06
     Grat
    -0.06
     Aur
    -0.06
    come
    -0.06
     Incoming
    -0.06
    ettel
    -0.06
    POSITIVE LOGITS
    Stuff
    0.07
    _amt
    0.07
    (chip
    0.07
     E
    0.06
    .echo
    0.06
     entertaining
    0.06
     같다
    0.06
     Watkins
    0.06
    �
    0.06
    (Book
    0.06
    Act Density 0.000%

    No Known Activations