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

    Neuronpedia

    INDEX
    Explanations

    personalized outreach

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     proportions
    -0.09
     East
    -0.08
    rei
    -0.08
     '''
    -0.08
    кости
    -0.08
     dë
    -0.08
     relinqu
    -0.07
    кость
    -0.07
    tml
    -0.07
     Вост
    -0.07
    POSITIVE LOGITS
    Recently
    0.09
    Nest
    0.08
    _recent
    0.08
    の記事
    0.08
     tailored
    0.08
     previamente
    0.08
     laborum
    0.08
     Spartan
    0.08
    Recent
    0.08
    (book
    0.08
    Act Density 0.014%

    No Known Activations