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

    Neuronpedia

    INDEX
    Explanations

    steps taken

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _uuid
    -0.07
     кам
    -0.07
     falsely
    -0.07
    (sum
    -0.07
    介绍
    -0.07
    たら
    -0.06
    _>
    -0.06
    .type
    -0.06
    .linalg
    -0.06
    _annotations
    -0.06
    POSITIVE LOGITS
    実
    0.07
    Mut
    0.06
    paredStatement
    0.06
    сед
    0.06
     sitio
    0.06
    ijd
    0.06
    มเต
    0.06
    tokenId
    0.06
    _serialize
    0.06
     Bahamas
    0.06
    Act Density 0.172%

    No Known Activations