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

    Neuronpedia

    INDEX
    Explanations

    will

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     portfolios
    -0.07
     Philosoph
    -0.07
    some
    -0.06
    ulk
    -0.06
    elic
    -0.06
    _k
    -0.06
     unos
    -0.06
    |array
    -0.06
    parser
    -0.06
    랙
    -0.06
    POSITIVE LOGITS
    manuel
    0.07
     할
    0.07
     حق
    0.07
     THEIR
    0.06
     GG
    0.06
    .modified
    0.06
    _owned
    0.06
    일
    0.06
     GI
    0.06
     tissue
    0.06
    Act Density 0.015%

    No Known Activations