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

    Neuronpedia

    INDEX
    Explanations

    keys

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     keys
    -0.85
    Keys
    -0.78
     Keys
    -0.71
     KEYS
    -0.64
    keys
    -0.57
    Portale
    -0.50
     spring
    -0.50
    KEYS
    -0.49
     mass
    -0.47
     loss
    -0.47
    POSITIVE LOGITS
    HideFlags
    0.68
     Arrondissement
    0.65
    BeginContext
    0.62
     Lordship
    0.60
    elemField
    0.59
    queryInterface
    0.58
     Shakspeare
    0.57
    utenants
    0.56
    }`}>
    0.56
     >=",
    0.56
    Act Density 0.124%

    No Known Activations