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

    Neuronpedia

    INDEX
    Explanations

    a

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     trải
    -0.07
     hlavy
    -0.07
     nghe
    -0.07
    .Logic
    -0.07
    ̆
    -0.07
     vydání
    -0.06
     mại
    -0.06
    .qual
    -0.06
    .week
    -0.06
    /output
    -0.06
    POSITIVE LOGITS
    :**
    0.06
    .•
    0.06
     panorama
    0.06
     CU
    0.06
    Pet
    0.06
    "${
    0.06
     kích
    0.06
     confirmation
    0.05
    ><
    0.05
     illustrates
    0.05
    Act Density 0.001%

    No Known Activations