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

    Neuronpedia

    INDEX
    Explanations

    censored/missing text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    eleration
    -0.09
    ிருந்த
    -0.08
    ulo
    -0.07
     lect
    -0.07
    tum
    -0.07
     totes
    -0.07
     Nicolas
    -0.07
    Lect
    -0.07
     ila
    -0.07
     learners
    -0.07
    POSITIVE LOGITS
     devise
    0.08
     Esp
    0.07
    0.07
    landing
    0.07
     sér
    0.07
     불
    0.06
     বলে
    0.06
     Sen
    0.06
    _BE
    0.06
     taper
    0.06
    Act Density 0.039%
    No Known Activations