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

    Neuronpedia

    INDEX
    Explanations

    Pet

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Dorm
    -0.07
    _zone
    -0.06
    Simulation
    -0.06
    ZONE
    -0.06
    otional
    -0.06
    (sort
    -0.06
    angen
    -0.06
     slogan
    -0.06
    (.)
    -0.06
     можете
    -0.05
    POSITIVE LOGITS
     अज
    0.07
     Erk
    0.07
    ες
    0.07
    syscall
    0.07
     fon
    0.07
     Nurses
    0.07
    emean
    0.06
    420
    0.06
    ................................................................
    0.06
     obtained
    0.06
    Act Density 0.002%

    No Known Activations