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

    Neuronpedia

    INDEX
    Explanations

    PLY

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Strings
    -0.07
     sha
    -0.06
     boarding
    -0.06
    Tab
    -0.06
    (lhs
    -0.06
     وزن
    -0.06
     материала
    -0.06
     seamless
    -0.06
    UMP
    -0.06
    Ê
    -0.06
    POSITIVE LOGITS
    @include
    0.07
    Henry
    0.07
    .Logf
    0.06
     khúc
    0.06
     hesitant
    0.06
    _logits
    0.06
     `;↵
    0.06
    _PE
    0.06
    函数
    0.06
    许多
    0.06
    Act Density 0.003%

    No Known Activations