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

    Neuronpedia

    INDEX
    Explanations

    Superscript/accent

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     inventions
    -0.07
     jobs
    -0.07
    forall
    -0.07
    lb
    -0.07
     par
    -0.07
     selling
    -0.07
     draw
    -0.07
     International
    -0.07
    nt
    -0.07
     바
    -0.07
    POSITIVE LOGITS
    ères
    0.09
    apanese
    0.06
    .sms
    0.06
    _sid
    0.06
    (xhr
    0.06
    .EntityFrameworkCore
    0.06
     memorable
    0.06
     अवध
    0.06
     викон
    0.05
     Müller
    0.05
    Act Density 0.041%

    No Known Activations