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

    Neuronpedia

    INDEX
    Explanations

    research studies

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     לצפיה
    -0.07
    𫐄
    -0.07
     scout
    -0.07
    פי
    -0.07
     multiplying
    -0.07
    🛌
    -0.07
    estimated
    -0.07
    톡
    -0.07
    .types
    -0.06
    uyện
    -0.06
    POSITIVE LOGITS
    _trace
    0.07
     WAN
    0.07
    摩擦
    0.07
    𝐠
    0.07
     khác
    0.07
    𝐜
    0.07
    'u
    0.07
    icism
    0.07
    ccc
    0.07
    𝐏
    0.07
    Act Density 0.113%

    No Known Activations