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

    Neuronpedia

    INDEX
    Explanations

    Bombings and WWII

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     wiki
    -0.07
     zeal
    -0.07
    信心
    -0.07
    ستر
    -0.07
    iona
    -0.07
     lithium
    -0.07
    inant
    -0.07
    圣地
    -0.06
    .ph
    -0.06
    .diff
    -0.06
    POSITIVE LOGITS
     Orwell
    0.08
    verts
    0.07
    /simple
    0.07
    ulnerable
    0.07
    Ἷ
    0.07
    ":{↵
    0.07
    清洗
    0.07
    ３
    0.07
     JSONObject
    0.07
    -uppercase
    0.07
    Act Density 0.008%

    No Known Activations