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

    Neuronpedia

    INDEX
    Explanations

    and

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .capture
    -0.07
     advisers
    -0.07
    create
    -0.07
    :update
    -0.06
    \Product
    -0.06
    affle
    -0.06
    Files
    -0.06
     먼저
    -0.06
     орган
    -0.06
     following
    -0.06
    POSITIVE LOGITS
    piring
    0.07
    ื้
    0.06
    ££
    0.06
    ůž
    0.06
     AO
    0.06
    Thing
    0.06
    Exact
    0.06
    =>$
    0.06
     Країна
    0.06
    �다
    0.06
    Act Density 0.105%

    No Known Activations