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

    Neuronpedia

    INDEX
    Explanations

    Technical documentation snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     opr
    -0.07
    莩
    -0.07
    باط
    -0.07
    얗
    -0.07
    .face
    -0.07
    تور
    -0.07
     melodies
    -0.07
    emes
    -0.07
    ottenham
    -0.07
    ToMany
    -0.07
    POSITIVE LOGITS
     visual
    0.07
     нек
    0.07
    慢性
    0.07
     called
    0.06
    凭什么
    0.06
     Column
    0.06
     שקיבל
    0.06
    請您提供
    0.06
    :"
    0.06
     turning
    0.06
    Act Density 0.433%

    No Known Activations