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

    Neuronpedia

    INDEX
    Explanations

    rot

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ibration
    -0.06
    _deps
    -0.06
    deps
    -0.06
     JTextField
    -0.06
     purchase
    -0.06
    (Client
    -0.06
    sys
    -0.06
     survivor
    -0.06
     td
    -0.06
     ‐
    -0.06
    POSITIVE LOGITS
    celand
    0.07
     Carson
    0.07
     Clarence
    0.07
     pristine
    0.06
     Fal
    0.06
     bolster
    0.06
     Kern
    0.06
    rol
    0.06
     integration
    0.06
     Orta
    0.06
    Act Density 0.001%

    No Known Activations