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

    Neuronpedia

    INDEX
    Explanations

    word meaning

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     unserer
    -0.06
     strang
    -0.06
    @Table
    -0.06
    543
    -0.06
    _DAT
    -0.06
     transporter
    -0.06
     πως
    -0.06
    лами
    -0.06
    while
    -0.06
    원의
    -0.06
    POSITIVE LOGITS
     Claim
    0.07
    _part
    0.06
    .commit
    0.06
    _Client
    0.06
     declaring
    0.06
    Assert
    0.06
     рад
    0.06
    _FL
    0.06
     Stad
    0.06
     stabilize
    0.06
    Act Density 0.090%

    No Known Activations