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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    OU
    -0.07
     bleiben
    -0.07
    _flutter
    -0.07
     symmetry
    -0.07
     Mechanics
    -0.07
     verificar
    -0.07
     blij
    -0.07
    PHY
    -0.07
    oldem
    -0.06
     относится
    -0.06
    POSITIVE LOGITS
    lhs
    0.06
    .GetLength
    0.06
     arist
    0.06
    (sem
    0.06
     Att
    0.06
     =============================================================================↵
    0.06
    .Ass
    0.05
    .getRaw
    0.05
     mơ
    0.05
     unclear
    0.05
    Act Density 0.410%

    No Known Activations