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

    Neuronpedia

    INDEX
    Explanations

    non-English words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Margins
    -0.07
    poses
    -0.07
     testament
    -0.06
    hw
    -0.06
    emon
    -0.06
    vature
    -0.06
    彗
    -0.06
    〽
    -0.06
     Independence
    -0.06
    ておく
    -0.06
    POSITIVE LOGITS
    леч
    0.07
    烦
    0.07
     NEXT
    0.07
    ⎢
    0.07
     nil
    0.07
     elites
    0.07
    🕓
    0.06
     사람들이
    0.06
     BUTTON
    0.06
    ją
    0.06
    Act Density 0.119%

    No Known Activations