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

    Neuronpedia

    INDEX
    Explanations

    question answering

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     spirits
    -0.07
    falls
    -0.07
     thuận
    -0.07
    垂
    -0.07
    谨
    -0.07
    clone
    -0.07
    翼
    -0.07
    培训机构
    -0.07
    墅
    -0.07
    peri
    -0.06
    POSITIVE LOGITS
    ম
    0.07
    (stmt
    0.07
     demonstrating
    0.07
    -efficient
    0.07
     ReturnType
    0.07
    ᆱ
    0.07
    Ὑ
    0.07
     plant
    0.07
     templateUrl
    0.07
    /select
    0.07
    Act Density 0.070%

    No Known Activations