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

    Neuronpedia

    INDEX
    Explanations

    Code errors

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    wm
    -0.06
    ’aut
    -0.06
     visite
    -0.06
     steward
    -0.06
    _fence
    -0.06
     giai
    -0.06
     Greg
    -0.06
    _depend
    -0.06
     "../
    -0.06
     Par
    -0.06
    POSITIVE LOGITS
    消费
    0.07
    様
    0.06
    ρεια
    0.06
    -seven
    0.06
    Ao
    0.06
    RuntimeObject
    0.06
    ющим
    0.06
    Ö
    0.06
    .VisualStudio
    0.06
    rapped
    0.06
    Act Density 0.007%

    No Known Activations