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

    Neuronpedia

    INDEX
    Explanations

    periods

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Seminar
    -0.07
     Third
    -0.07
    Working
    -0.06
     seminar
    -0.06
    Friday
    -0.06
     led
    -0.06
     strategic
    -0.06
     ride
    -0.06
     outstanding
    -0.06
     reserves
    -0.06
    POSITIVE LOGITS
     buluş
    0.07
    арх
    0.07
    decess
    0.06
    μπο
    0.06
    Dock
    0.06
     гал
    0.06
    (phi
    0.06
     отдель
    0.06
     плат
    0.06
    (forms
    0.06
    Act Density 0.010%

    No Known Activations